ClawdGo uses a self-play training loop with weakest-first scheduling and cross-session memory to raise AI agents' security awareness scores from 80.9 to 96.9 across 12 taxonomy dimensions.
Defensive refusal bias: How safety alignment fails cyber defenders
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Refusal-ablated LLMs outperform aligned models on code-grounded localization and early executable patch generation, while aligned models retain advantages on shallow diagnostic tasks under neutral wording.
LLMs fall for deceptive traps at higher rates than humans, lack the human attention-diversion effect, and exploit traps 73.4% of the time even after recognizing them in reasoning.
citing papers explorer
-
Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents
ClawdGo uses a self-play training loop with weakest-first scheduling and cross-session memory to raise AI agents' security awareness scores from 80.9 to 96.9 across 12 taxonomy dimensions.
-
Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis
Refusal-ablated LLMs outperform aligned models on code-grounded localization and early executable patch generation, while aligned models retain advantages on shallow diagnostic tasks under neutral wording.
-
Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
LLMs fall for deceptive traps at higher rates than humans, lack the human attention-diversion effect, and exploit traps 73.4% of the time even after recognizing them in reasoning.