LiL vulnerabilities are more severe than ecosystem and conventional bugs and drop LLM-based repair Pass@1 by ~10.8%, with three categories often at 0% success.
From prompt injections to sql injection attacks: How protected is your llm-integrated web application?
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 3polarities
background 3representative citing papers
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
AgentSpec introduces a customizable DSL for runtime enforcement of safety constraints on LLM agents, achieving over 90% prevention of unsafe code actions, zero hazardous embodied actions, and 100% AV compliance in evaluations.
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
citing papers explorer
-
Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities
LiL vulnerabilities are more severe than ecosystem and conventional bugs and drop LLM-based repair Pass@1 by ~10.8%, with three categories often at 0% success.
-
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
-
AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
AgentSpec introduces a customizable DSL for runtime enforcement of safety constraints on LLM agents, achieving over 90% prevention of unsafe code actions, zero hazardous embodied actions, and 100% AV compliance in evaluations.
-
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.