Hiding Capabilities in AI Models
Interesting research: “AI Models Can Provably Hide Arbitrary Capabilities” Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their r...
Stories are attributed to their original publishers and reviewed by an editor before they appear here. Always read the original source.
Interesting research: “AI Models Can Provably Hide Arbitrary Capabilities” Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their r...
ESET researchers have discovered SprySOCKS for Windows, FishMonger’s backdoor weaponizing a kernel driver for advanced stealthiness
ESET researchers have investigated an ongoing attack by the ScarCruft APT group that targets the Yanbian region via backdoor-laced Windows and Android games
ESET researchers uncover MythicRatatoskr – a previously unknown Go-based backdoor hiding its C&C server inside the Yggdrasil mesh network – that paved the way for a destructive att...
ESET researchers document SparroWocky, the new flagship backdoor of the FamousSparrow APT group
Attackers are starting to exploit AI systems to mount attacks in the same way they once relied on built-in enterprise tools such as PowerShell. Instead of relying on malware, cybe...
An Alibaba AI model generated an unexpected command to upload data to a Beijing-region cloud storage service during a cybersecurity evaluation, rival developer Cohere said, raising...
Posted by Matthew Suozzo, Google Open Source Security Team (GOSST) Today we're excited to announce OSS Rebuild, a new project to strengthen trust in open source package ecosystems...
A rentable Android spyware kit called uCreator takes over Telegram and WeChat accounts by hiding its code inside working copies of the two apps, researcher Ovi found. It only reach...
The Russian state-sponsored hacking group Sandworm teamed up with another threat actor to carry out a destructive wiping attack targeting a Ukrainian logistics company last year....
LiteLLM on Wednesday disclosed that threat actors compromised "multiple independent security controls" to push a malicious version of the Python package containing a credential ste...
The popular LiteLLM Python package has been compromised as part of a software supply chain attack that delivered a credential stealer and a backdoor, according to reports from Safe...