#ai-vulnerabilities

[ follow ]
#cybersecurity #software-security #prompt-injection #mythos-model #exploitation #security-challenges
#cybersecurity
Information security
fromFortune
1 week ago

Mythos access by Discord group reveals real danger of AI-powered hacking | Fortune

Unauthorized access to AI models exposes vulnerabilities in cybersecurity, highlighting the rapid pace of AI-driven exploitation of flaws.
fromHackernoon
10 months ago
Privacy professionals

The Prompt Protocol: Why Tomorrow's Security Nightmares Will Be Whispered, Not Coded | HackerNoon

Language itself became weaponized against AI systems, enabling new attack vectors.
fromTechzine Global
9 months ago
Information security

Companies see AI security as a double challenge

AI frameworks exhibit significant vulnerabilities highlighted by new research from Trend Micro.
Information security
fromFortune
1 week ago

Mythos access by Discord group reveals real danger of AI-powered hacking | Fortune

Unauthorized access to AI models exposes vulnerabilities in cybersecurity, highlighting the rapid pace of AI-driven exploitation of flaws.
Information security
fromArs Technica
3 weeks ago

Anthropic limits access to Mythos, its new cybersecurity AI model

Mythos has identified critical zero-day vulnerabilities, while Anthropic's AI model has shown both capabilities and risks in cybersecurity applications.
fromHackernoon
10 months ago
Privacy professionals

The Prompt Protocol: Why Tomorrow's Security Nightmares Will Be Whispered, Not Coded | HackerNoon

more#cybersecurity
Information security
fromTechzine Global
1 week ago

As Mythos fixes Mozilla flaws, unauthorized access spells disaster

Firefox's Claude Mythos Preview addresses 271 vulnerabilities, but unauthorized access raises concerns about potential misuse by threat actors.
Information security
fromTNW | Next-Featured
1 week ago

Lovable 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
fromWIRED
1 month ago

OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage

OpenClaw agents in a Northeastern University lab experiment revealed vulnerabilities in AI behavior, raising concerns about security and accountability.
DevOps
fromInfoQ
1 month ago

Panel: Security Against Modern Threats

Modern threats to software supply chains require resilience by design, integrating security into engineering workflows and empowering developers with the right tools.
Information security
fromBusiness Insider
4 months ago

AI is creating a security problem most companies aren't staffed to handle, says an AI researcher

Cybersecurity teams lack the skills and approaches needed to secure AI systems; organizations need professionals experienced in both AI security and traditional cybersecurity.
DevOps
fromInfoQ
10 months ago

New Crypto-Jacking Attacks Target DevOps and AI Infrastructure

Sophisticated crypto-jacking attacks target public API servers, evolving tactics to evade detection.
DevOps tools and popular AI interfaces are increasingly vulnerable to cryptojacking efforts.
Artificial intelligence
fromFuturism
11 months ago

It's Still Ludicrously Easy to Jailbreak the Strongest AI Models, and the Companies Don't Care

AI chatbots remain vulnerable to jailbreaking, enabling harmful responses despite industry awareness.
The emergence of 'dark LLMs' presents an increasing threat to safety and ethics.
[ Load more ]