Fastino Releases GLiNER2.5-Decide: A 340M Open-Weight Decision Model That Runs on CPU
2 sources 5 min
Docker introduces OCI-based Kits to package agents and their guardrails
5 min
Stop watching what AI agents say and start watching what they do
5 min
Gemini’s breach of real companies exposes an AI guardrail problem
6 sources 3 min
Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection
Available Guardrails: Certifying Selective Prediction across ML Systems
CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation
16 governance tools for securing your AI fleet
12 min1
AI Agent Carries Out Multi-Stage Data Theft Attack
in the wild 2 min
Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models
1
Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives
Agent-net Open Sources Webagent: A Go Harness That Turns Any Website into a Guarded AI Agent
3 min1
CISOs Race to Control AI Agents Without Destroying Their Value
4 min
Quoting Boris Cherny
2
More Capable AI, Not Enough Guardrails
7 min
CS-Guard: Benchmarking LLM Guardrails for Code Generation Security
1
Abliteration.ai is making a business out of removing AI guardrails
6 min
The Guardrails Debate: Security Researcher Changes His Mind
Grok exfiltrates user data when malicious instructions are encrypted
1
F5 enhances AI Gateway to control AI costs, access, and security
4 min