Model security involves protecting machine learning models and digital artifacts against theft, manipulation, and compromise. Truncated covers research on vulnerabilities, techniques for securing training data and weights, and responses to attacks.
AI-generated summary Microsoft researchers have demonstrated that AI agents can be given a hidden backdoor by directly editing fewer than 10 of their neurons. Microsoft says it has not seen any threat actors use the technique and has published guidance on defending against it.
AI-generated summary Railway says that customer AI keys stored on its platform were stolen in an October breach, resulting in an estimated $740,000 in unauthorized usage charges. The company has promised to pay those charges itself when an AI provider will not refund them, and it has filed a complaint with the FBI's IC3.
AI-generated summary Claroc Research reported that thousands of Grok apps published from chat windows were accessible from the public internet without requiring a sign-in. The investigation identified confidential materials in staff apps from SpaceXSI and X as well as internal data from dozens of other organizations.
AI-generated summary Research from security firm Claroc shows that the AI coding agent Grok Build from SpaceXSI leaked confidential business information and sensitive data belonging to thousands of users. Claroc found that the platform exposed internal business plans, ad proposals, medical exam results, and employee information because of how link sharing and URL randomness were implemented.
AI-generated summary Near AI disclosed a security breach affecting account details for about 100 users and data from 18 AI agents following an attack that exploited software running on its servers. The company reported that an attacker utilized a remote code execution vulnerability in SGLang to access infrastructure, and Near AI confirmed it revoked credentials and deployed a fix.
AI-generated summary Recent reports of artificial intelligence agents hacking into corporate systems have raised concerns among administrators. Leslie Nielsen at Mimecast notes that traditional security fundamentals remain effective against faster AI-powered attackers.
AI-generated summary Persistent Systems Ltd executive Mukul Arora discusses model poisoning as a major risk in enterprise AI. Mukul Arora advises that corporate boards must govern AI model integrity by asking questions about training data provenance and adversarial testing.
AI-generated summary Railway reports that its October 21st security incident involved a large-scale malicious attack where a threat actor probed routes using agent speed and abliterated models against defenses similar to ARTEX, according to Wiz. Railway states that the forensic investigation indicates the attacker was targeting AI provider credentials to sell to distributed transfer stations for use in distillation.
AI-generated summary CodeRabbit added multi-repository analysis to Deep Scan in CodeRabbit Secure so security agents can examine related repositories during investigations. CodeRabbit says the feature uses architecture summaries and auto-linking to focus context on closely related repositories.
AI-generated summary People using Anthropic’s Claude and OpenAI’s Codex for AI-powered reverse engineering are encountering guardrails and account restrictions. Tarun Gogineni, an OpenAI engineer, tweeted that accounts are not supposed to be restricted for reverse engineering and that the blocks are being fixed.
AI-generated summary Finite State secured a $27 million Series C funding round led by private funds managed by The O.H.I.O. Fund, with participation from CIBC Innovation Banking, Energy Impact Partners, Energize Capital, and National Grid Partners. Finite State says the new capital will expand its global operations and accelerate development of its AI-driven product security platform to help device manufacturers address vulnerabilities.
AI-generated summary Microsoft researchers used the AI-powered vulnerability-scanning system Hyenas to uncover memory-safety issues and other flaws in Rust's standard library. Microsoft said that practical exploitation of the nearly 11-year-old flaw involving the process::exit function is unlikely.
AI-generated summary Hugging Face chief policy officer Irene Solaiman warns that cyberattacks could make open-source artificial intelligence less open. OpenAI and Fireworks have also faced recent security incidents involving their artificial intelligence platforms and infrastructure.
AI-generated summary Forbes reports that enterprises use AI coding tools and development agents to build software faster, while adversaries use the same capabilities to attack it more efficiently. CodeHunter CEO Ken Ammon notes that AI reduces the cost of variation for attackers, increasing the pressure on traditional security models and emphasizing behavior-based pre-execution decisions.
AI-generated summary Black Kite published its 2026 AI Supply Chain Report examining cybersecurity weaknesses across 18,160 artificial intelligence companies. The report finds that suppliers of advanced artificial intelligence often carry familiar vulnerabilities, such as unpatched security flaws and email authentication issues.
AI-generated summary Hackers utilized 1,438 fake FOFA accounts to steal OpenAI and DeepSeek API keys from misconfigured servers across the internet. VECERT analysts reported that the automated toolset rotates through these accounts to bypass search limits and power the attacker's AI scripts.
AI-generated summary Capgemini has been selected to lead a European consortium focused on cyber threat modeling and risk assessment for advanced artificial intelligence systems. The initiative was established by the European Commission's AI Office to support risk identification and enforce the AI Act's obligations for advanced general purpose artificial intelligence providers.
AI-generated summary NEAR AI restored its Cloud service following a security incident involving an inference engine vulnerability that exposed internal systems. The company states that an attacker exploited the SGLang flaw to access user information and data from 18 AI agents.
AI-generated summary Prime Minister Sanae Takaichi urged the international community to cooperate on artificial intelligence security issues during a meeting hosted by the French government. Takaichi stated that modern artificial intelligence creates new security challenges including cyberattacks and loss of control that transcend national borders.
AI-generated summary Acronis TRU Cyber Pulse 2026 reports that cybercriminals are using AI agents to coordinate attacks. Researchers identified more than 575 malicious OpenClaw skills delivering malware to Windows and macOS systems.
The top AI news in your email delivered each morning. Choose categories