Secure AI Weekly

238 Results / Page 1 of 27

A humorous illustration showing ANS verifying AI agents with PKI while a spaghetti monster claims “I identify as a microservice”

todayMay 26, 2025

  • 110
close

Secure AI Weekly ADMIN

Towards Secure AI Week 20 — Identity, Jailbreaks, and the Future of Agentic AI Security

This week’s stories highlight the rapid emergence of new threats and defenses in the Agentic AI landscape. From OWASP’s DNS-inspired Agent Name Service (ANS) for verifying AI identities to real-world exploits like jailbreakable “dark LLMs” and prompt-injected assistants like GitLab Duo, the ecosystem is shifting toward identity-first architecture and layered ...

Abstract AI security background with glitch effects and shield symbol, representing trust and resilience in generative AI.

todayMay 19, 2025

  • 142
close

Secure AI Weekly ADMIN

Towards Secure AI Week 19 —  AI Agents Under Attack, Evaluation Becomes Strategy

This week’s stories highlight a critical evolution in AI risk: the shift from isolated agent failures to system-level compromise in Agentic AI architectures and memory-based applications. From Princeton’s demonstration of cryptocurrency theft via false memory injection to Fortnite’s AI Darth Vader being manipulated into swearing within an hour of launch, ...

Abstract AI security background with glitch effects and shield symbol, representing trust and resilience in generative AI.

todayMay 12, 2025

  • 169
close

Secure AI Weekly ADMIN

Towards Secure AI Week 18 — LLM Jailbreaks Hit New Highs, AI Security Market Accelerates

As LLMs become embedded across enterprise applications, new red-teaming research shows jailbreak success rates surpassing 87% on models like GPT-4—even under safety-aligned settings. Techniques such as multi-turn roleplay, token-level obfuscation, and cross-model attacks continue to outpace current safeguards. Meanwhile, insider misuse and unfiltered GenAI outputs pose growing risks, prompting calls ...

Abstract AI security background with glitch effects and shield symbol, representing trust and resilience in generative AI.

todayMay 5, 2025

  • 126
close

Secure AI Weekly + Trusted AI Blog admin

Towards Secure AI Week 17 — AI Guardrails Under Pressure as Jailbreaking Techniques Advance

Enterprise use of generative AI is expanding, but so is the sophistication of attacks targeting these systems. New jailbreak methods are achieving nearly 100% success rates, even on well-aligned models like GPT-4 and Llama3, while recent research exposes vulnerabilities in memory, prompt interpretation, and cross-tool coordination protocols like MCP. At ...

todayApril 28, 2025

  • 133
close

Secure AI Weekly + Trusted AI Blog admin

Towards Secure AI Week 16 — Can Your AI Agents Really Coordinate Safely?

As generative AI adoption accelerates, so do the security challenges that come with it. New research shows that even advanced large language models (LLMs) can be jailbroken with evolving techniques, while multi-agent AI systems introduce fresh risks at the communication and coordination layers. Cybercriminals are also scaling attacks using GenAI ...

todayApril 2, 2025

  • 41
close

Secure AI Weekly + Trusted AI Blog admin

Towards Secure AI Week 12 – New NIST AI Security Efforts

NIST AI 100-2 E2025. Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations NIST, March, 2025 The National Institute of Standards and Technology (NIST) has released a report titled “Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations” (NIST AI 100-2 E2025). The report categorizes AML ...