Persuasion in LLMs works by redirecting a small set of attention heads to copy the target option token instead of reasoning over evidence, via a rank-one routing feature that can be directly edited or removed.
Proceedings of the 16th ACM workshop on artificial intelligence and security , pages=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 6roles
dataset 1polarities
use dataset 1representative 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.
ARGUS defends LLM agents from context-aware prompt injections by tracking information provenance and verifying decisions against trustworthy evidence, reducing attack success to 3.8% while retaining 87.5% task utility.
Adversarial compromise of tool outputs misleads agentic AI via breadth and depth attacks, revealing that epistemic and navigational robustness are distinct and often trade off against each other.
SafeHarbor introduces a hierarchical memory-augmented guardrail with adversarial rule extraction and entropy-driven self-evolution to balance safety and utility in LLM agents.
citing papers explorer
-
How LLMs Are Persuaded: A Few Attention Heads, Rerouted
Persuasion in LLMs works by redirecting a small set of attention heads to copy the target option token instead of reasoning over evidence, via a rank-one routing feature that can be directly edited or removed.
-
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.
-
ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
ARGUS defends LLM agents from context-aware prompt injections by tracking information provenance and verifying decisions against trustworthy evidence, reducing attack success to 3.8% while retaining 87.5% task utility.
-
How Adversarial Environments Mislead Agentic AI?
Adversarial compromise of tool outputs misleads agentic AI via breadth and depth attacks, revealing that epistemic and navigational robustness are distinct and often trade off against each other.
-
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
SafeHarbor introduces a hierarchical memory-augmented guardrail with adversarial rule extraction and entropy-driven self-evolution to balance safety and utility in LLM agents.
- SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces