Artificial Intelligence
AI red team specialist details his methods for manipulating AI guardrails through jailbreaking and data poisoning, helping developers harden machine learning models.
Hi, what are you looking for?
SecurityWeek
All posts tagged "LLM"
Artificial Intelligence
LLMs can write complex Rego and Cedar code in seconds, but a single missing condition or hallucinated attribute can quietly dismantle your organization’s least-privilege...
Artificial Intelligence
Among them, 23,000 hosts were persistently responsible for the majority of activity observed over 293 days of scanning.
Artificial Intelligence
An LLMjacking operation has been targeting exposed LLMs and MCPs at scale, for commercial monetization.
Artificial Intelligence
Threat actors are hunting for misconfigured proxy servers to gain access to APIs for various LLMs.
Artificial Intelligence
Attackers intercepting network traffic can determine the conversation topic with a chatbot despite end-to-end encrypted communication.
Artificial Intelligence
How security posture management for AI can protect against model poisoning, excessive agency, jailbreaking and other LLM risks.
Artificial Intelligence
Building secure AI agent systems requires a disciplined engineering approach focused on deliberate architecture and human oversight.
Artificial Intelligence
From prompt injection to emergent behavior, today’s curious AI models are quietly breaching trust boundaries.
Artificial Intelligence
The latest release of the xAI LLM, Grok-4, has already fallen to a sophisticated jailbreak.
Artificial Intelligence
AI-made decisions are in many ways shaping and governing human lives. Companies have a moral, social, and fiduciary duty to responsibly lead its take-up.
Artificial Intelligence
New "Echo Chamber" attack bypasses advanced LLM safeguards by subtly manipulating conversational context, proving highly effective across leading AI models.
Artificial Intelligence
Microsoft offers $10,000 in rewards to researchers who can manipulate a realistic simulated LLM-integrated email client.
Artificial Intelligence
Google has showcased the capabilities of its Big Sleep LLM agent, which found a previously unknown exploitable memory safety issue in SQLite.
Artificial Intelligence
Cybersecurity startup Simbian has launched three LLM AI Agents that work as virtual employees but with the speed, stamina, and accuracy of robots.
Compliance
A new CMMC review and reform task force will conduct a comprehensive review of the program.
Hacker Conversations
Vulnerabilities
Vulnerabilities
The flaws could allow attackers to access and modify data, and cause system unavailability and request-response desynchronization.
Cybersecurity Funding
Malware & Threats
Hacker Conversations