Plus: Microsoft scolded for a “cascade” of security failures, AI-generated lawyers send fake legal threats, a data broker quietly lobbies against US privacy legislation, and more.

It’s been a week since the world avoided a potentially catastrophic cyberattack. On March 29, Microsoft developer Andres Freund disclosed his discovery of a backdoor in XZ Utils, a compression tool widely used in Linux distributions and thus countless computer systems worldwide. The backdoor was inserted into the open source tool by someone operating under the persona “Jia Tan” after years of patient work building a reputation as a trustworthy volunteer developer. Security experts believe Jia Tan is the work of a nation-state actor, with clues largely pointing to Russia, although definitive attribution for the attack is still outstanding.

In early 2022, a hacker operating under the name “P4x” took down the internet of North Korea, after the country’s hackers had targeted him. This week, WIRED revealed P4x’s true identity as Alejandro Caceres, a 38-year-old Colombian American. Following his successful attack on North Korea, Caceres pitched the US military on a “special forces”-style offensive hacking team that would carry out operations similar to the one that made P4x famous. The Pentagon eventually declined, but Caceres has launched a startup, Hyperion Gray, and plans to further pursue his controversial approach to cyberwarfare.

In mid-February, millions of people lost internet access after three undersea cables in the Arabian Sea were damaged. Some blamed Houthi rebels in Yemen, who had been attacking ships in the region, but the group denied it had sabotaged the cables. But the rebel attacks are still likely to blame—albeit, in a bizarre way. A WIRED analysis of satellite images, maritime data, and more found that the cables were likely damaged by the trailing anchor of a cargo ship that the Houthi rebels had bombed. The ship drifted for two weeks before finally sinking, crossing paths with the cables at the time they were damaged.

The myth that Google Chrome’s Incognito mode provides adequate privacy protections can finally be put to rest. As part of a settlement over Google’s Incognito privacy claims and practices, the company has agreed to delete “billions” of records collected while users browsed in Incognito mode. It will also further clarify how much user data can be collected by Google and third parties while Incognito is enabled, and take further steps to protect user privacy. There are other privacy-focused browsers that can replace Chrome. But if you’re still using it, make sure to update it to patch some serious security flaws.

But that’s not all. Each week, we round up the security and privacy news we didn’t cover in depth ourselves. Click the headlines to read the full stories. And stay safe out there.

A 58-year-old hospital systems administrator pleaded guilty this week to US federal charges after he was caught using another man’s name for more than 30 years. Matthew David Keirans allegedly stole the identity of William Woods in 1988, when the two men worked at a hot dog cart in Albuquerque, New Mexico, according to the US Attorney's Office for the Northern District of Iowa. Over the decades, Keirans obtained employment, bank accounts, loans, and insurance, and paid taxes, under the Woods name. Keirans even had a child whose last name is Woods.

The real William Woods, meanwhile, reportedly learned that someone else was using his identity in 2019. At the time, Woods was unhoused and living in Los Angeles. He contacted a bank where “William Woods” had an account, providing his real Social Security card and California ID card to prove his identity. However, he could not answer the security questions to gain access. The bank called Keirans—who was pretending to be Woods—and Keirans convinced the bank employee that the real Woods should not have access to the accounts. The Los Angeles Police Department then arrested the real Woods and charged him with identity theft after Keirans provided officers with false documents and information.

In a nightmarish twist, during judicial proceedings, the real Woods accurately maintained that “William Donald Woods” was his true identity, prompting the court to order him to a mental institution. The real Woods ultimately spent 428 days in jail and 147 days in a mental hospital before his release.

The real Woods then continued to work to regain his true identity, eventually contacting authorities after learning that Keirans worked at a hospital in Iowa City. Investigators later confirmed the real Woods’ identity after obtaining a DNA test. Confronted with the evidence, Keirans confessed to a series of crimes and now faces a maximum sentence of 32 years in prison, a $1.25 million fine, and five years of supervised release.

**US Review Board Slams Microsoft for ‘Cascade of Avoidable Security Failures’**

The White-House mandated Cyber Safety Review Board issued a scathing report against Microsoft this week, accusing the tech giant of failing to stop a “preventable” intrusion by China-backed hackers of hundreds of Microsoft Exchange Online email accounts. To gain access to email accounts belonging to 22 organizations and 500 individuals worldwide, the hackers, known as Storm-0558, stole a Microsoft cryptographic key. The CSRB report chastises the company for failing to detect “the compromise of its cryptographic crown jewels,” inadequate security practices, and a “corporate culture that deprioritized both enterprise security investments and rigorous risk management,” among a “cascade” of other defeats.

The report also found that Microsoft still does not know how Storm-0558 obtained its key, accusing the company of making false statements after it initially claimed that the key was accidentally included in an April 2021 “crash dump.” The company has since updated its explanation of the intrusion to say that it still does not know how the hackers obtained the key. The CSRB issued 25 recommended steps that Microsoft—a major government contractor whose systems protect highly sensitive information—should take to better protect its systems.

**AI-Generated Lawyers Caught Spewing Fake Legal Threats**

The owner of the website Tedium received legal threats from a nonexistent “law firm” charging the publication with a copyright violation. The thing is, the “lawyers” behind the complaint were AI-generated. The “law firm” accused Tedium of using a photograph without the owner’s consent, and a "copyright infringement" notice offered to supposedly settle the matter, if only Tedium would agree to properly credit the photo’s “owner” and link out to their website. This was, of course, a backlink scam designed to boost the SEO ranking of the fake copyright holder’s page. Only this time, the scam was bolstered by a cast of AI-generated characters: a hot-shot team of young, "skilled lawyers" purportedly specializing in creative rights and commercial law.

**Data Behemoth Enlists Lobbyists Against Effort in US to Limit Deals With Spies**

An internal feud is underway in the US Congress over the fate of a beleaguered spy program called Section 702 and the commercial deals that US intelligence agencies have struck in recent years with global data brokers, purchasing information that government agents typically need a warrant to obtain. Consequently, the UK owner of LexisNexis—an “amalgam of publishers and data brokers, stitched together into a single information giant”—has retained the services of a Washington, DC, lobbying firm to engage with federal lawmakers over “potential privacy, data security, breach notification, data broker, and FISA reform legislation.” Politico reports that the company, RELX, previously used the firm, Venable, to combat privacy legislation aimed at restricting the kinds of personal data companies are allowed to sell to law enforcement.

**‘Weapon Scanners’ Eyed by New York’s Surveillant Mayor Boasts Abysmal Track Record**

New York City mayor Eric Adams is hastening his crusade against subway violence with a plan to test weapons scanners that claim to use artificial intelligence to detect whether commuters are carrying blades and firearms. Documents obtained by Hell Gate reveal what Adams failed to disclose at a press conference last week: that data already in the city’s hands show the technology is only rarely useful. After police officers permitted to carry firearms were factored out of one study at a Bronx hospital, the scanners were found to be accurate less than 1 percent of the time. (All told, more than 85 percent of the time, the scanners cast false suspicion on New Yorkers who were found to be unarmed.) The move by Adams follows New York governor Kathy Hochul’s deployment of hundreds of National Guard soldiers in the city’s subway systems. Adams first addressed a spate of homicides and stabbings across the city in March by sending hundreds of police officers underground to search commuters' bags at well over 100 subway stations—a tactic that roused resistance from a few locals this week who smashed ticket machines and disabled security cameras at a midtown station to protest the surveillance surge.

Identity Thief Lived as a Different Man for 33 Years

DerbyNet 9.0 suffers from a remote SQL injection vulnerability in print/render/racer.inc.

CVE ID: CVE-2024-30923

Description:  
An SQL Injection vulnerability has been discovered in DerbyNet version 9.0, specifically within the `print/render/racer.inc` component. This vulnerability allows remote attackers to execute arbitrary code and disclose sensitive information by exploiting improper sanitization of the `where` clause in Racer Document Rendering.

Vulnerability Type: SQL Injection

Vendor of Product: DerbyNet - Available on GitHub: https://github.com/jeffpiazza/derbynet

Affected Product Code Base: DerbyNet - v9.0

Affected Component: print/render/racer.inc

Attack Type: Remote

Impact:  
- Code execution: True  
- Information Disclosure: True

Attack Vectors:  
The vulnerability is present in the `print/render/racer.inc` component of DerbyNet, due to insufficient sanitization of the `where` parameter within the URL. Attackers can manipulate SQL queries by injecting malicious SQL commands through the `where` parameter, as demonstrated in the following URL:  
- `http://127.0.0.1:8000/render-document.php/award/GoldCupAwardDocument?where=1`

This manipulation could lead to unauthorized access to database information and potential code execution on the server hosting the application.

Discoverer: Valentin Lobstein

References:  
- Official website: http://derbynet.com  
- Source code on GitHub: https://github.com/jeffpiazza/derbynet

DerbyNet 9.0 print/render/racer.inc SQL Injection

DerbyNet 9.0 suffers from a remote SQL injection vulnerability in ajax/query.slide.next.inc.

    CVE ID: CVE-2024-30928Description:An SQL Injection vulnerability has been discovered in DerbyNet version 9.0, particularly within the `ajax/query.slide.next.inc` file. This vulnerability allows remote attackers to execute arbitrary code and disclose sensitive information by exploiting the unvalidated `classids` parameter used in constructing SQL queries. This parameter is not properly sanitized before being included in the SQL statement, leading to a critical risk of SQL Injection.Vulnerability Type: SQL InjectionVendor of Product: DerbyNet - Available on GitHub: https://github.com/jeffpiazza/derbynetAffected Product Code Base: DerbyNet - v9.0Affected Component: ajax/query.slide.next.incAttack Type: RemoteImpacts:- Code execution: True- Information Disclosure: TrueAttack Vectors:The vulnerability is primarily exploited by manipulating the `classids` parameter in the user's request to the `ajax/query.slide.next.inc` file. The lack of adequate input validation allows attackers to inject malicious SQL code through this parameter. Example attack vectors include:- Direct exploitation:- `http://127.0.0.1:8000/action.php?query=slide.next&mode=racer&classids=1`- Boolean-based blind SQL Injection:- Payload: `query=slide.next&mode=racer&classids=1) AND 4365=4365 AND (6880=6880`- UNION query SQL Injection:- Payload: `query=slide.next&mode=racer&classids=-3890) UNION ALL SELECT NULL,NULL,CHAR(113,107,120,122,113)||CHAR(79,97,117,85,112,79,82,85,75,114,65,66,118,100,117,107,79,118,111,104,67,105,87,86,72,110,107,119,113,86,106,107,115,100,110,109,98,77,85,115)||CHAR(113,118,120,120,113),NULL,NULL,NULL,NULL,NULL-- rDzQ`These vectors demonstrate how an attacker could manipulate SQL queries to potentially access or manipulate database information unauthorizedly.Discoverer: Valentin LobsteinReferences:- Official website: http://derbynet.com- Source code on GitHub: https://github.com/jeffpiazza/derbynet

DerbyNet 9.0 ajax/query.slide.next.inc SQL Injection

DerbyNet version 9.0 suffers from a cross site scripting vulnerability in racer-results.php.

CVE ID: CVE-2024-30927

Description:  
A Cross-Site Scripting (XSS) vulnerability is present in DerbyNet version 9.0, specifically within the `racer-results.php` component. This issue allows remote attackers to execute arbitrary code through the improper handling of the `racerid` parameter. The vulnerability is notably present within the HTML `<title>` tag, where the `racerid` parameter value is dynamically inserted directly into the page content without any sanitization or encoding.

Vulnerability Type: Cross-Site Scripting (XSS)

Vendor of Product: DerbyNet - Available on GitHub: https://github.com/jeffpiazza/derbynet

Affected Product Code Base: DerbyNet - v9.0

Affected Component: racer-results.php

Attack Type: Remote

Impact: Code execution

Attack Vectors:  
The XSS vulnerability can be exploited by inserting malicious JavaScript code into the `racerid` parameter of the URL. For example:  
- `http://127.0.0.1:8000/racer-results.php?racerid=</title><script>alert(1)</script>`

This method demonstrates how an attacker could manipulate the `racerid` parameter to inject and execute arbitrary JavaScript within the context of a user's session.

Discoverer: Valentin Lobstein

References:  
- Official website: http://derbynet.com  
- Source code on GitHub: https://github.com/jeffpiazza/derbynet

DerbyNet 9.0 racer-results.php Cross Site Scripting

DerbyNet version 9.0 suffers from a cross site scripting vulnerability in photo-thumbs.php.

CVE ID: CVE-2024-30925

Description:  
A Cross-Site Scripting (XSS) vulnerability exists in DerbyNet version 9.0, specifically within the `photo-thumbs.php` component. This issue enables a remote attacker to execute arbitrary code through the improper handling of the `racerid` and `back` parameters. The vulnerability arises because the application dynamically generates URLs for navigation without adequately sanitizing these parameters, thus allowing the injection of malicious scripts.

Vulnerability Type: Cross-Site Scripting (XSS)

Vendor of Product: DerbyNet - Available on GitHub: https://github.com/jeffpiazza/derbynet

Affected Product Code Base: DerbyNet - v9.0

Affected Component: photo-thumbs.php

Attack Type: Remote

Impact: Code execution

Attack Vectors:  
The XSS vulnerability can be exploited through manipulation of the `racerid` and `back` parameters in the URL. Examples of such manipulation include:  
- http://127.0.0.1:8000/photo-thumbs.php?repo=head&racerid=</script><script>alert(1)</script>  
- http://127.0.0.1:8000/photo-thumbs.php?back="><script>alert(1)</script></div>

These URLs demonstrate how an attacker could inject and execute arbitrary JavaScript within the context of the user's browser session.

Discoverer: Valentin Lobstein

References:  
- Official website: http://derbynet.com  
- Source code on GitHub: https://github.com/jeffpiazza/derbynet

DerbyNet 9.0 photo-thumbs.php Cross Site Scripting

DerbyNet version 9.0 suffers from a cross site scripting vulnerability in render-document.php.

    CVE ID: CVE-2024-30920Description:A Cross Site Scripting (XSS) vulnerability has been identified in DerbyNet v9.0, specifically within the `render-document.php` component. This vulnerability allows a remote attacker to execute arbitrary code via crafted URLs. The root cause of the vulnerability is the application's failure to properly sanitize user input in document rendering paths, which permits the injection of malicious scripts.Vulnerability Type: XSS (Cross Site Scripting)Vendor of Product:DerbyNet - https://github.com/jeffpiazza/derbynetAffected Product Code Base:DerbyNet - v9.0Affected Component:render-document.phpAttack Type:RemoteImpact:Code executionRoot Cause:The vulnerability arises from the application's display of debug information, including `ORIG_SCRIPT_FILENAME`, `DOCUMENT_URI`, `SCRIPT_NAME`, and `PHP_SELF`. These debug outputs improperly handle user-supplied input by not sanitizing it before inclusion in the output, leading directly to XSS vulnerabilities when malicious inputs are rendered by the browser.Attack Vectors:The vulnerability can be exploited with URLs such as:- `http://127.0.0.1:8000/render-document.php/racer/<img src=x onerror=alert(1)>`- `http://127.0.0.1:8000/render-document.php/<img src=x onerror=alert(1)>`Discoverer:Valentin LobsteinReferences:- http://derbynet.com- https://github.com/jeffpiazza/derbynet

DerbyNet 9.0 render-document.php Cross Site Scripting

As “P4x,” Alejandro Caceres single-handedly disrupted the internet of an entire country. Then he tried to show the US military how it can—and should—adopt his methods.

A Vigilante Hacker Took Down North Korea’s Internet. Now He’s Taking Off His Mask

It's critical for security teams to stay vigilant not only when it comes to major security issues, but also with minor lags in security best practice.

Tim Chase, Global Field CISO, Lacework

April 2, 2024

3 Min Read

Source: Anna Berkut via Alamy Stock Photo

COMMENTARY

The saying "put yourselves in the shoes of a hacker" has long been part of defensive security strategies. Today, in the fast-paced and evolving threat landscape, this statement is truer than ever for chief information security officers (CISOs) and security teams at scale.

As cyber threats continue to evolve in 2024, CISOs and security teams must be prepared for everything from supply chain risks to zero-day exploits to deepfakes to cloud targeting and more. By ensuring visibility across your infrastructure, encouraging employee training, and supporting bug bounty programs, your organization will harden its security posture and be better prepared to fend off rising threats this year. Let's dive a bit deeper into each: 

**Creating Security Allies Out of Your Team**

Recent cyberattacks have shown us that the level of sophistication and damage caused by malicious actors is not slowing down. The MOVEit data breach that leaked the personal information of more than 11 million people shows the raw scale of modern attacks. Similar breaches at MGM and Caesars were exacerbated by the FBI struggling to stop the cyber gang behind the incident. 

While the security team can't befriend everyone in an organization, they can focus on education internally in order to train staff on risks and create clear communication that covers important issues. If hackers are staying up to date and getting educated on the latest threats and risks, we should as well. Creating a "security champions" program across the organization is a great way to embed security. One team member from marketing, finance, legal, etc., can plug in to your team and be a liaison for security that helps push pertinent cybersecurity information out across the company.

**Supporting Bug Bounty Programs**

Rather than being anxious and shunning bug bounty programs, CISOs and security teams should reward good behavior. I encourage employees to attend hackathons — even if it's only to observe or learn at first. It's one step in the right direction for security education. For more hands-on cybersecurity learning, I also like to arrange company-wide competitions and games that encourage employees to figure out how cybercrime could potentially happen.

There is no better way to prepare for a real breach than with a simulation. It forces the team to work together, strategize, and agree on a solution. The increased need for internal cybersecurity education and support for bug bounty programs is only going to continue growing in order to keep up with rising threats.

**If All Else Fails, Focus on Visibility**

Visibility is a foundational principle that suggests you can't secure what you don't know about. Lack of a security team's visibility is a gold rush for hackers because they typically infiltrate an organization's network via hidden or sneaky entry points. If you don't have visibility, there will undoubtedly be a way in. Without visibility into all traffic within an organization's infrastructure, threat actors can continue to lurk in the network and grant themselves access to the organization's most sensitive data.

With 93% of malware hiding behind encrypted traffic but only 30% of security professionals claiming to have visibility, it's no wonder that there were more ransomware attacks in the first half of 2023 than in all of 2022. Once a cybercriminal has made their way into the network, time is limited. Only with visibility can the cybercriminal be stopped from wreaking havoc and gaining access to company data.

When cybersecurity professionals can better understand the mysterious nature of hackers and how they work, they can better protect their own systems and valuable customer data. It's critical to stay vigilant not only when it comes to major security issues, but also with minor lags in security best practice. We saw this with the recent breach of Hewlett Packard, which was undertaken by the same group behind 2020's SolarWinds breach. Some of the most sophisticated cybercriminals are also incredibly opportunistic, taking advantage of any split-second lapse in otherwise-tight security plans. Ensure you take the steps above to stay ahead of looming threats. 

**About the Author(s)**

Global Field CISO, Lacework

Tim Chase is the Global Field CISO at Lacework and has worked in information security for over 15 years in various roles, including leading security teams focusing on Cloud and AppSec. He has extensive experience working at the board and executive level to promote security and guide decision-making.

Instilling the Hacker Mindset Organizationwide

By Waqas
New AI-Dodging Phishing Attack AI Security and Exploits Machine Learning.
This is a post from HackRead.com Read the original post: Cybercriminals Beta Test New Attack to Bypass AI Security

Hackers develop a new attack (Conversation Overflow) to bypass AI security. Learn how this technique fools Machine Learning and what businesses can do to stay protected.

A recent discovery by SlashNext threat researchers reveals a dangerous cyberattack method termed “Conversation Overflow.” This technique involves cloaked emails designed to bypass machine learning (ML) security controls, allowing malicious payloads to infiltrate enterprise networks.

In a typical Conversation Overflow attack, cybercriminals employ cloaked emails designed to deceive ML tools into categorizing them as harmless. These emails contain two distinct sections: one visible to the recipient, prompting them to take action such as entering credentials or clicking links and another hidden portion filled with innocuous text.

Threat actors exploit ML algorithms by strategically inserting blank spaces to separate these sections, often focusing on deviations from “known good” communications rather than identifying malicious content.

According to SlashNext’s research shared with Hackread.com ahead of publication on Tuesday, this novel approach poses a significant challenge to traditional cybersecurity measures, which rely on databases of “known bad” signatures. Unlike these methods, ML systems analyze patterns to detect anomalies, making them susceptible to manipulation by attackers mimicking legitimate communication styles.

Once a Conversation Overflow attack breaches security defences, attackers can deliver seemingly genuine messages requesting credential reauthentication, particularly targeting high-level executives. The stolen credentials are then sold on dark web forums, highlighting the lucrative nature of such cybercrime.

SlashNext threat researchers express deep concern regarding the potential ramifications of this attack becoming widespread. There is a significant risk that cybercriminals are actively developing an entirely new toolkit, which could exacerbate the impact of such attacks, potentially leading to devastating consequences for organizations and individuals alike.

> _“This is not your same old credential harvesting attack, because it is smart enough to confuse certain sophisticated AI and ML engines. From these findings, we should conclude that cyber crooks are morphing their attack techniques in this dawning age of AI security. As a result, we are concerned that this development reveals an entirely new toolkit being refined by criminal hacker groups in real-time today.”_
> 
> SlashNext

The implications of this discovery are profound, signalling a shift in cybercriminal tactics to exploit vulnerabilities in AI and ML-driven security platforms. As cyber criminals adapt and refine their techniques, it becomes increasingly imperative for organizations to remain vigilant and proactive in fortifying their defences.

1.  Ivanti VPN Flaws Exploited to Spread KrustyLoader Malware
2.  Telekopye Toolkit Used as Telegram Bot to Scam Marketplace Users
3.  RIG Exploit Toolkit Spread CeidPageLock Malware to Hijack Browsers

Cybercriminals Beta Test New Attack to Bypass AI Security

By Deeba Ahmed
While Fujitsu did not disclose in-depth details, the company confirmed investigating a cyberattack that may have led to a data breach.
This is a post from HackRead.com Read the original post: Fujitsu Scrambles After Malware Attack: Customer Data Potentially Breached

Japanese tech giant Fujitsu is investigating a potential data leak after malware infected company systems – This could expose the personal information of customers and employees.

Fujitsu is investigating a possible data leak caused by a malware infection that may have allowed unauthorized access to personal information, according to its press release on Friday.

Fujitsu confirmed the presence of malware on multiple work computers, suggesting a potential entry point for unauthorized access. The company quickly launched an investigation. Initial probing has revealed that the malware could have accessed and extracted sensitive personal and customer information. 

“We discovered that files containing personal information and customer information could be illegally taken out,” Fujitsu stated in its press release.

However, the tech giant is yet to confirm the nature of malware used to target its computers, the number of affected computers, and the type of data breached in the attack. Fujitsu discovered the cyberattack on 15 March but has not disclosed other details, including whether contact details, passwords, and payment details were compromised and the time of the attack.

It has implemented strict security measures, isolating affected computers and strengthening network surveillance. The company has disconnected affected systems from its network and is investigating the type of malware used, the nature of the cyberattack, and the method of the intrusion. 

Fujitsu has not disclosed who has been affected, including employees, corporate customers, and citizens using the company’s technologies. 

The company claims to be informing “the targeted individuals and customers” about the possible data breach and has notified the Personal Information Protection Commission, Japan’s data protection authority.

“To date, we have not received any reports that personal information or information about our customers has been misused” the company concluded.

Fujitsu is a leading Japanese ICT company, employing 124,000 people in over 100 countries. The company has been involved in wrongful convictions due to bugs in its Horizon computer software.

1.  Top Japanese dating app Omiai hacked; 1.71 million users at risk
2.  CutOut.Pro AI Tool Data Breach: Hacker Leak 20 Million User Info
3.  Acer Data Breach: Hacker Claims to Sell 160GB Trove of Stolen Data
4.  American Express Users Impacted by 3rd-Party Vendor Data Breach
5.  Nissan Confirms Data Breach Affected 100,000 Users and Employees

Tag

#acer