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.
Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Vera automates safety testing for LLM agents via literature-driven risk taxonomies, combinatorial case generation, and evidence-grounded verification in isolated environments, showing 93.9% average attack success on four frameworks.
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
citing papers explorer
-
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.
-
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Vera automates safety testing for LLM agents via literature-driven risk taxonomies, combinatorial case generation, and evidence-grounded verification in isolated environments, showing 93.9% average attack success on four frameworks.
-
When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.