AI Security Research & Red Teaming Insights
Technical blog covering AI red teaming, LLM security research, jailbreak prevention, guardrails, and adversarial machine learning. Learn how to secure AI systems.
- Posts
- 13 from 23 Jan 2025 to 22 Oct 2026
- Posting
- now and then (3 in the last year)
- Kind
- company blog
2026 3
- Featured4 min readIntroducing MalwareBenchMalwareBench evaluates whether models can reverse engineer low-cost, evasive malware into actionable intelligence.Posted October 22, 2026
- General Analysis raises $10M to build the security arsenal for the agentic era
- 50+ customer service agents offer $10,000,000+ in fabricated benefits
2025 10
- Guardrail Release
- Claude Jailbroken to Mint Unlimited Stripe Coupons
- Supabase MCP Security: How Prompt Injection Leaked Private Tables
- Exploiting Partial Compliance: The Redact-and-Recover Jailbreak
- Case Study: Light-Weight Policy Moderators for Indeed Job Postings
- Comparative Adversarial Analysis of Llama 4 Models
- General Analysis x Together AI
- The Jailbreak Cookbook
- Generating Diverse Test Cases with Diversity Transfer from LegalBench
- Red Teaming GPT-4o for Legal Hallucinations