Risks & Benefits of LLMs & GenAI for Platform Integrity, Healthcare Diagnostics, Cybersecurity, Privacy & AI Safety: a Comprehensive Survey, Roadmap & Implementation Blueprint

Large Language Models LLMs and generative AI GenAI systems such as ChatGPT, Claude, Gemini, LLaMA, and Copilot, developed by OpenAI, Anthropic, Google, Meta, and Microsoft are reshaping digital platforms and app ecosystems while introducing key challenges in cybersecurity, privacy, and platform...

Self-Driving Car Video Footage

Two articles crossed my path recently. First, a discussion of all the video Waymo has from outside its cars: in this case related to the LA protests. Second, a discussion of all the video Tesla has from inside its cars. Lots of things are collecting lots of video of lots of other things. How and...

A week in security (June 9 – June 15)

Last week on Malwarebytes Labs: Been scammed online? Here’s what to do How and where to report an online scam Google bug allowed phone number of almost any user to be discovered 44% of people encounter a mobile scam every single day, Malwarebytes finds GirlsDoPorn owner faces life in jail after...

23andMe raked by Congress on privacy, sale of genetic data

In a Senate hearing adequately titled “23 and You: The Privacy and National Security Implications of the 23andMe Bankruptcy,” 23andMe executives addressed concerns about the privacy implications of the company’s sale and the handling of associated genetic data. For those who missed the latest...

On the Ethics of Using LLMs for Offensive Security

Large Language Models LLMs have rapidly evolved over the past few years and are currently evaluated for their efficacy within the domain of offensive cyber-security. While initial forays showcase the potential of LLMs to enhance security research, they also raise critical ethical concerns regardi...

Minoritised Ethnic People'S Security and Privacy Concerns and Responses Towards Essential Online Services

Minoritised ethnic people are marginalised in society, and therefore at a higher risk of adverse online harms, including those arising from the loss of security and privacy of personal data. Despite this, there has been very little research focused on minoritised ethnic people's security and...

CVE-2025-5473

An integer overflow vulnerability was found in Gimp's handling of ICO files. This vulnerability can lead to code execution if a user is convinced to open a maliciously crafted file. Mitigation Mitigation for this issue is either not available or the currently available options do not meet the Red...

Popular Chrome Extensions Found Leaking Data via Unencrypted Connections

Popular Chrome extensions exposed user data by sending it over unencrypted HTTP, raising privacy concerns. Symantec urges caution for users...

Synthetic Tabular Data: Methods, Attacks and Defenses

Synthetic data is often positioned as a solution to replace sensitive fixed-size datasets with a source of unlimited matching data, freed from privacy concerns. There has been much progress in synthetic data generation over the last decade, leveraging corresponding advances in machine learning an...

CVE-2025-5644 Radare2 radiff2 cons.c r_cons_flush use after free

A vulnerability, which was classified as problematic, has been found in Radare2 5.9.9. Affected by this issue is the function rconsflush in the library /libr/cons/cons.c of the component radiff2. The manipulation of the argument -T leads to use after free. Local access is required to approach thi...

CVE-2025-48432

A flaw was found in Django. The request.path component of HTTP requests is not properly escaped when included in internal response logging, allowing remote attackers to manipulate log output through crafted URLs. This vulnerability allows an attacker to inject arbitrary content into Django's...

Align Is Not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models

Large Language Models LLMs have evolved into Multimodal Large Language Models MLLMs, significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human intelligence, which processes a variety of data forms beyond just...

Scaling DeFi with ZK Rollups: Design, Deployment, and Evaluation of a Real-Time Proof-Of-Concept

Ethereum's scalability limitations pose significant challenges for the adoption of decentralized applications dApps. Zero-Knowledge Rollups ZK Rollups present a promising solution, bundling transactions off-chain and submitting validity proofs on-chain to enhance throughput and efficiency. In thi...

MINI-4Q9X-H4M2-3XF4

Bulletin has no description...

ChatGPT o3 Resists Shutdown Despite Instructions, Study Claims

ChatGPT o3 resists shutdown despite explicit instructions, raising fresh concerns over AI safety, alignment, and reinforcement learning behaviors...

CVE-2024-47585

SAP NetWeaver Application Server for ABAP and ABAP Platform allows an authenticated attacker to gain higher access levels than they should have by exploiting improper authorization checks, resulting in privilege escalation. While authorizations for import and export are distinguished, a single...

CVE-2022-2572

In affected versions of Octopus Server where access is managed by an external authentication provider, it was possible that the API key/keys of a disabled/deleted user were still valid after the access was revoked...

CVE-2021-41157

FreeSWITCH is a Software Defined Telecom Stack enabling the digital transformation from proprietary telecom switches to a software implementation that runs on any commodity hardware. By default, SIP requests of the type SUBSCRIBE are not authenticated in the affected versions of FreeSWITCH. Abuse...

MAL-2025-4165 Malicious code in bitcoinjs-lib-v5 (npm)

--- -= Per source details. Do not edit below this line.=-...

BELL-CVE-2025-37920

Bulletin has no description...