Artificial Intelligence
Attackers could inject prompts into a GitHub issue and take over the AI agent designed to automatically triage the issue.
Hi, what are you looking for?
SecurityWeek
All posts tagged "AI"
Artificial Intelligence
Dragos has published a report describing how threat actors used Claude AI in an attack on a water and drainage utility in Mexico.
Artificial Intelligence
AI red team specialist details his methods for manipulating AI guardrails through jailbreaking and data poisoning, helping developers harden machine learning models.
Artificial Intelligence
Dubbed Bleeding Llama, the heap out-of-bounds read issue can be exploited remotely, without authentication.
Artificial Intelligence
Advanced Account Security provides stronger login methods, more secure account recovery, shorter sessions, and training exclusion.
Artificial Intelligence
Google, Microsoft, Amazon Web Services, Nvidia, OpenAI, Reflection and SpaceX will provide resources to help augment warfighter decision-making in complex operational environments,” the Defense...
Artificial Intelligence
The maximum reward for a zero-click Pixel Titan M exploit with persistence has increased to $1.5 million.
Artificial Intelligence
Threat actors are relying on social engineering to lure users into downloading files containing malicious instructions.
Artificial Intelligence
With Mythos signaling a new era of near-instant exploitation, Anthropic positions Claude Security to help defenders keep pace.
Artificial Intelligence
An attacker could have planted a malicious configuration to execute commands outside the sandbox.
Artificial Intelligence
Only with the right platform and an agentic, AI-driven defense, will enterprises be able to protect themselves in the agentic era.
Artificial Intelligence
The tech giant found that many indirect prompt injection attempts are harmless, but some malicious exploits have also been identified.
Artificial Intelligence
From autonomous code generation to decision-making systems that initiate actions without human intervention, the industry is entering a new phase.
Artificial Intelligence
The Trump administration is vowing to crack down on foreign tech companies’ exploitation of U.S. artificial intelligence models.
Artificial Intelligence
The Israel-based company, which just emerged from stealth mode, was founded by cloud and security experts from RSA, McAfee, and Unity.
Artificial Intelligence
360 Digital Security Group claims to have uncovered 1,000 vulnerabilities using AI, including at the Tianfu Cup hacking contest.
Artificial Intelligence
Palo Alto Networks has developed Zealot, a multi-agent penetration testing PoC capable of reconnaissance, exploitation, and exfiltration.
Artificial Intelligence
All the flaws could have also been found by an elite human researcher, according to Mozilla.
Artificial Intelligence
Researchers discovered a remote code execution vulnerability and cybercriminals are using its reputation to deliver malware.
Artificial Intelligence
A White House official said the administration is engaging with advanced AI labs about their models and the security of software.
Cybercrime
Amir Barati, an alleged member of the Mabna Institute, was indicted for targeting universities, private organizations, and government entities in the US and abroad.
Artificial Intelligence
Vulnerabilities
Hacker Conversations
Vulnerabilities
Artificial Intelligence
Vulnerabilities
Malware & Threats