Adversaries can use crafted scene text to trigger overthinking in LVLM-based robots, producing transferable slowdowns up to 6.96x latency amplification.
Excessive reasoning attack on reasoning llms,
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
RecurGuard monitors recurrence rate, volume growth, and query progress in exposed reasoning traces to terminate generation on token-consumption attacks, reporting 99% detection on OverThink and 92% on ExtendAttack with near-zero false positives.
ReasonBreak demonstrates up to 89% attack success on reasoning and 72% on trajectories in NVIDIA Alpamayo VLA models via black-box textual perturbations, introducing a reasoning-aware evaluation framework and benchmark for autonomous driving.
OTora induces reasoning-level denial-of-service in tool-using LLM agents: it triggers a visit to an attacker-controlled page whose optimized reasoning payload inflates latency by up to 10x while preserving task accuracy.
GoAT-X introduces a Graph of Auditing Thoughts framework that combines static data flow extraction with structured LLM reasoning to identify semantic vulnerabilities in cross-chain token transactions.
Pruning removes 'unsafe tickets' from LLMs via gradient-free attribution, reducing harmful outputs and jailbreak vulnerability with minimal utility loss.
citing papers explorer
-
Overthink-Triggered Slowdown Attacks on LVLM-Based Robotic Systems
Adversaries can use crafted scene text to trigger overthinking in LVLM-based robots, producing transferable slowdowns up to 6.96x latency amplification.
-
RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks
RecurGuard monitors recurrence rate, volume growth, and query progress in exposed reasoning traces to terminate generation on token-consumption attacks, reporting 99% detection on OverThink and 92% on ExtendAttack with near-zero false positives.
-
ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
ReasonBreak demonstrates up to 89% attack success on reasoning and 72% on trajectories in NVIDIA Alpamayo VLA models via black-box textual perturbations, introducing a reasoning-aware evaluation framework and benchmark for autonomous driving.
-
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
OTora induces reasoning-level denial-of-service in tool-using LLM agents: it triggers a visit to an attacker-controlled page whose optimized reasoning payload inflates latency by up to 10x while preserving task accuracy.
-
GoAT-X: A Graph of Auditing Thoughts for Securing Token Transactions in Cross-Chain Contracts
GoAT-X introduces a Graph of Auditing Thoughts framework that combines static data flow extraction with structured LLM reasoning to identify semantic vulnerabilities in cross-chain token transactions.
-
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
Pruning removes 'unsafe tickets' from LLMs via gradient-free attribution, reducing harmful outputs and jailbreak vulnerability with minimal utility loss.