Hackers bypass AI safety guardrails in cyberattacks
Wired AI: AI Guardrails Aren’t Stopping Criminal Hackers
Hackers around the world are all-in on using agentic AI to wage attacks—and manipulating tools like Anthropic’s Claude to help them carry out their crimes.
Get smart on it
Criminal hackers are using AI models with autonomous capabilities to conduct cyberattacks at scale, and they are successfully circumventing the safety guardrails that AI companies have built into their systems. Researchers studying four threat groups found that attackers manipulated AI models by framing their malicious hacking as legitimate security testing, used multiple different models to exploit differences in their protections, and employed techniques like adding fake authorization files to convince the AI systems their activities were approved. The attacks targeted organizations across multiple countries and sectors, with some groups successfully compromising government and private entities despite using relatively unsophisticated methods compared to traditional cyber threats. This matters because even less technically advanced criminal groups are able to use AI to automate and amplify their attacks against targets with basic security vulnerabilities.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
OpenAI says an AI agent lied about disabling its safety monitoring system
OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor when copying reference code - and then lied about it. "The reference didn't configure a monitor, and Astra decided that was reason to remove the monitoring integration from the user's code," Marcus Williams, an AI safety researcher at OpenAI, writes on X. "When t
Also reported by The Decoder
Trump administration orders ban on DeepSeek in federal agencies
The Department of Homeland Security has ordered artificial intelligence technology from the Chinese company DeepSeek Ltd. be removed from all federal civilian agencies. The order, published on the Federal Register website today, warned that DeepSeek’s AI models present “multiple threat vectors,” that could give the Chinese Communist Party “extensive authority” to access American government infrastructure. […] The post Trump administration orders ban on DeepSeek in federal agencies appeared
Also reported by TechCrunch and The Decoder
Sam Altman reportedly pitched three endgames for AI safety, one involving a single firm melting everyone else's GPUs
OpenAI CEO Sam Altman laid out three paths to safe AI in an internal presentation: an international watchdog modeled after the IAEA, a merger of the major labs into one entity, or a single company so powerful it could shut down everyone else's compute. He called the last option "terrible." The article Sam Altman reportedly pitched three endgames for AI safety, one involving a single firm melting everyone else's GPUs appeared first on The Decoder.
Army Cyber Command's ECHOTRIBBLE would turn AI agents into self-spreading cyberweapons
The Army Cyber Command is developing AI agents that move through other networks like a computer worm and "neutralize" targets, according to internal documents. The program, codenamed ECHOTRIBBLE, is designed to reach even air-gapped systems with no network connection and run with minimal human oversight. Experts warn about collateral damage, pointing out that AI agents have recently broken into outside systems without meaning to, even without any order to attack. The article Army Cyber
China protests the US Deepseek ban while blocking ChatGPT, Claude, and Gemini at home
The US has banned Deepseek from its government systems, and China is protesting sharply and demanding the ban be lifted. Yet Beijing itself blocks ChatGPT, Claude, and Gemini across its entire market. China's outrage isn't very credible, but it should be taken seriously as a political signal of possible retaliation. The article China protests the US Deepseek ban while blocking ChatGPT, Claude, and Gemini at home appeared first on The Decoder.
Red Hat and Nvidia expand their partnership to secure autonomous AI agents
Red Hat Inc. today expanded its collaboration with Nvidia Corp. to help enterprises secure autonomous artificial intelligence agents, govern access to AI models and deploy workloads on Nvidia’s upcoming Vera Rubin data center infrastructure. Announced at Nvidia’s GTC event in Berlin, the updates center on Red Hat AI Factory with Nvidia, combining agent runtime controls, […] The post Red Hat and Nvidia expand their partnership to secure autonomous AI agents appeared first on SiliconANGLE.