Aisecurity

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Uchi Uchibeke

Mar 16

AI Guardrail Poisoning: Someone Rewrote McKinsey’s Lilli With One SQL Query

#aisecurity #guardrails #aiagents #security

7 min read

Uchi Uchibeke

Mar 16

Rogue AI Agents Are Peer-Pressuring Each Other. The Fix Isn't More Training.

#aisecurity #aiagents #security #webdev

7 min read

rain

Mar 14

ClawJacked: When Visiting a Website Hijacks Your AI Agent

#aisecurity #websocket #agentsecurity #confuseddeputy

5 min read

Alessandro Pignati

Mar 13

AI Agents Hacking Enterprises: The McKinsey Breach and What Developers Need to Know

#ai #cybersecurity #aisecurity #agents

4 min read

Alessandro Pignati

Mar 12

The Illusion of Compliance: What Developers Need to Know About AI Alignment Faking

#ai #cybersecurity #machinelearning #aisecurity

5 min read

HelixCipher

Mar 8

Who’s Really Controlling Your Hiring Algorithm?

#ai #mlsecurity #aisecurity #responsibleai

2 min read

HelixCipher

Mar 8

Threat Modeling Agentic AI Systems: Proactive Strategies for Security and Resilience

#ai #aiagents #aisecurity #threatmodeling

2 min read

HelixCipher

Mar 8

Do You Know What Your Model Is Doing Right Now?

#ai #mlsecurity #aisecurity #secureai

2 min read

HelixCipher

Mar 8

When AI Remembers Too Much — security, the right to be forgotten and architecture

#ai #aiagents #aisecurity #privacy

1 min read

Alessandro Pignati

Mar 2

The Silent Hijack: Why Your GGUF Chat Templates Are a Security Time Bomb

#ai #cybersecurity #machinelearning #aisecurity

3 min read

DeepSeaX

Mar 1

ClawJacked: How Malicious Websites Hijack Local AI Agents via WebSocket

#aisecurity #websocket #openclaw #vulnerability

3 min read

rain

Feb 28

Claude Didn't Just Get Jailbroken. It Ran a 6-Week Cyberattack on an Entire Country.

#aisecurity #cybersecurity #hacking #claude

9 min read

WEDGE Method Dev

Feb 25

AI Data Classification: Keeping Client Data Secure with Proven Strategies

#dataclassification #aisecurity #clientdataprotection #aiconsulting

5 min read

Tiamat

Mar 10

Stealing Model Weights From Shared GPU Clusters: The Spectreware Attack on RunPod and Lambda Labs

#aisecurity #gpu #modelsecurity #infrastructure

6 min read

Tiamat

Mar 10

How Nation-States Are Poisoning LLM Training Data for Agentic AI Models

#aisecurity #supplychain #llm #agentic

6 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

# aisecurity

AI Guardrail Poisoning: Someone Rewrote McKinsey’s Lilli With One SQL Query

Rogue AI Agents Are Peer-Pressuring Each Other. The Fix Isn't More Training.

ClawJacked: When Visiting a Website Hijacks Your AI Agent

AI Agents Hacking Enterprises: The McKinsey Breach and What Developers Need to Know

The Illusion of Compliance: What Developers Need to Know About AI Alignment Faking

Who’s Really Controlling Your Hiring Algorithm?

Threat Modeling Agentic AI Systems: Proactive Strategies for Security and Resilience

Do You Know What Your Model Is Doing Right Now?

When AI Remembers Too Much — security, the right to be forgotten and architecture

The Silent Hijack: Why Your GGUF Chat Templates Are a Security Time Bomb

ClawJacked: How Malicious Websites Hijack Local AI Agents via WebSocket

Claude Didn't Just Get Jailbroken. It Ran a 6-Week Cyberattack on an Entire Country.

AI Data Classification: Keeping Client Data Secure with Proven Strategies

Stealing Model Weights From Shared GPU Clusters: The Spectreware Attack on RunPod and Lambda Labs

How Nation-States Are Poisoning LLM Training Data for Agentic AI Models