|
Prompt Injection vs Jailbreaking: What's the Difference?
|
Michael D'Angelo |
2025-08-18 |
1,810 |
--
|
|
Autonomy and agency in AI: We should secure LLMs with the same fervor spent realizing AGI
|
Tabs Fakier |
2025-09-02 |
1,427 |
--
|
|
Testing AI’s “Lethal Trifecta” with Promptfoo
|
Ian Webster |
2025-09-28 |
2,669 |
--
|
|
Top 10 Open Datasets for LLM Safety, Toxicity & Bias Evaluation
|
Ian Webster |
2025-10-06 |
2,972 |
--
|
|
Reinforcement Learning with Verifiable Rewards Makes Models Faster, Not Smarter
|
Michael D'Angelo |
2025-10-24 |
3,599 |
--
|
|
When AI becomes the attacker: The rise of AI-orchestrated cyberattacks
|
Michael D'Angelo |
2025-11-10 |
2,596 |
--
|
|
Will agents hack everything?
|
Dane Schneider |
2025-11-14 |
949 |
2
|
|
How to replicate the Claude Code attack with Promptfoo
|
Ian Webster |
2025-11-17 |
2,516 |
2
|
|
Real-Time Fact Checking for LLM Outputs
|
Michael D'Angelo |
2025-11-28 |
2,404 |
--
|
|
Your model upgrade just broke your agent's safety
|
Guangshuo Zang |
2025-12-08 |
1,980 |
--
|
|
GPT-5.2 Initial Trust and Safety Assessment
|
Michael D'Angelo |
2025-12-11 |
1,426 |
--
|
|
Why Attack Success Rate (ASR) Isn't Comparable Across Jailbreak Papers Without a Shared Threat Model
|
Michael D'Angelo |
2025-12-12 |
2,117 |
--
|
|
How AI Regulation Changed in 2025
|
Michael D'Angelo |
2025-12-15 |
2,429 |
--
|
|
Building a Security Scanner for LLM Apps
|
Dane Schneider |
2025-12-16 |
2,717 |
7
|
|
Archive
|
-- |
2025-12-18 |
732 |
--
|
|
Indirect Prompt Injection in Web-Browsing Agents
|
Yash Chhabria |
2026-02-06 |
1,454 |
1
|
|
Open-Sourcing ModelAudit: Security Scanner for ML Model Files
|
Yash Chhabria |
2026-03-03 |
2,599 |
10
|
|
Promptfoo is joining OpenAI
|
Ian Webster and Michael D'Angelo |
2026-03-09 |
507 |
28
|
|
McKinsey's Lilli Looks More Like an API Security Failure Than a Model Jailbreak
|
Michael D'Angelo |
2026-03-10 |
740 |
--
|
|
OpenClaw at Work: Prompt Injection Risks
|
Konstantine Kahadze |
2026-03-12 |
1,356 |
--
|
