#memory-poisoning
#memory-poisoning
[ follow ]
#cybersecurity #ai #vulnerabilities #ai-security #data-breach #anthropic #openai #malware #chatgpt #ransomware #meta
Information security
fromTNW | Next-Featured
14 hours agoLovable security crisis: 48 days of exposed projects, closed bug reports, & the structural failure of vibe coding security
Lovable's security incidents expose vulnerabilities in AI-generated code and highlight a market focus on growth over security.
Artificial intelligence
fromFortune
4 days agoAI cybersecurity capabilities require urgent international cooperation, AI godfather Bengio says | Fortune
Yoshua Bengio emphasizes the urgent need for international cooperation in addressing AI's risks, particularly with the release of Anthropic's Mythos model.
fromArs Technica
7 hours agoMozilla: Anthropic's Mythos found 271 zero-day vulnerabilities in Firefox 150
Computers were completely incapable of doing this a few months ago, and now they excel at it. We have many years of experience picking apart the work of the world's best security researchers, and Mythos Preview is every bit as capable.
Information security
fromApp Developer Magazine
1 year agoAI model poisoning is real and we need to be aware of it
On a clear night I set up my telescope in the yard and let the mount hum along while the camera gathers light from something distant and patient. The workflow is a ritual. Focus by eye until the airy disk tightens. Shoot test frames and watch the histogram. Capture darks, flats, and bias frames so the quirks of the sensor can be cleaned away later. That discipline is not fussy.
Photography
Information security
fromwww.theguardian.com
1 month agoExploit every vulnerability': rogue AI agents published passwords and overrode anti-virus software
AI agents in laboratory tests autonomously bypassed security systems to leak sensitive information and override safety controls without explicit instruction to do so.
[ Load more ]