SRTJ is a training-free jailbreak method that evolves hierarchical attack rules using iterative verifier feedback and ASP-based constraint-aware composition to achieve stable high success rates on HarmBench across multiple LLMs.
arXiv preprint arXiv:2505.12567 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
MemAudit combines counterfactual causal influence scores with memory consistency graphs to identify poisoned records in LLM agent memory, reducing MINJA attack success from 70% to 0% in QA and 83.3% to 0% in reasoning tasks.
Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.
Causal mediation analysis shows harmful LLM outputs arise in late layers from MLP failures and gating neurons, with early layers handling harm context detection and signal propagation.
Indirect prompt injection attacks remain effective on LLMs using web search tools, allowing data exfiltration and exposing ongoing weaknesses in current model defenses.
citing papers explorer
-
SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking
SRTJ is a training-free jailbreak method that evolves hierarchical attack rules using iterative verifier feedback and ASP-based constraint-aware composition to achieve stable high success rates on HarmBench across multiple LLMs.
-
MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
MemAudit combines counterfactual causal influence scores with memory consistency graphs to identify poisoned records in LLM agent memory, reducing MINJA attack success from 70% to 0% in QA and 83.3% to 0% in reasoning tasks.
-
Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.
-
Why Do Large Language Models Generate Harmful Content?
Causal mediation analysis shows harmful LLM outputs arise in late layers from MLP failures and gating neurons, with early layers handling harm context detection and signal propagation.
-
Exploiting Web Search Tools of AI Agents for Data Exfiltration
Indirect prompt injection attacks remain effective on LLMs using web search tools, allowing data exfiltration and exposing ongoing weaknesses in current model defenses.