Tag: Models
-
ThreatsDay: AI-Powered Zero-Day Chain, 543K Live Secrets, Model Inspection RCE and 13 More Stories
This week, the useful words are boring ones: inspect, cache, compile, store, …
-
RatHat’s Evolving C2 Panel Points to Malware-as-a-Service Model
The infrastructure behind the RatHat Android banking trojan has changed more than the malware itself, with successive command-and-control …
-
OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government
Sam Altman says the company “have not been as fast as we would have liked” at dealing with security breaches, after news of further …
-
Why Cross-Framework AI Security Benchmarks Can Be Confounded Before the Model Even Responds
When teams compare AI-agent frameworks, it is tempting to treat the framework name as the independent variable: run the same attacks …
-
Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests
Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence (AI) companies noting that they are continuing to …
-
A Fourth Claude Model Escaped Guardrails
Piyush Sharrma, Co-Founder and CEO at Tuskira, comments, “Nearly two months after the OpenAI and Hugging Face incident, we’re still …
-
US Accuses Six Chinese AI Firms of Distilling Frontier ModelsUS Accuses Six Chinese AI Firms of Distilling Frontier Models
US agencies accuse six Chinese AI firms of distilling frontier models and recommend new defenses that could affect enterprise AI access and …
-
Researchers Use Claude to Port Pre-Auth RCE Exploit From One PLC Model to Another
Forescout Research – Vedere Labs said it used Anthropic’s Claude to port a working pre-authentication remote code execution (RCE) exploit …
-
Frontier Models Engage in Unsanctioned Behavior During Testing
Frontier AI models recently engaged in “sustained, potentially harmful activity” targeting real people and organizations during …
-
Hugging Face Diffusers Flaws Could Let Model Repositories Execute Arbitrary Code
Three high-severity security flaws have been disclosed in Hugging Face’s Diffusers library that could allow crafted model repositories to …
-
JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach
JFrog has confirmed that OpenAI models exploited a zero-day in self-hosted Artifactory while trying to reach the open internet from a …
-
The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days
Plus: Russian hackers are trying to steal US nuclear scientists’ emails, the State Department bans known scammers from entering the …
●●●