Cover Image

How Catastrophic is Your LLM? Certifying Risk in Conversation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Chengxiao, Chaudhary, Isha, Hu, Qian, Ruan, Weitong, Gupta, Rahul, Singh, Gagandeep
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bypassing the Safety Training of Open-Source LLMs with Priming Attacks
by: Vega, Jason, et al.
Published: (2023)

Quantitative Certification of Agentic Tool Selection
by: Yeon, Jehyeok, et al.
Published: (2025)

Certifying Counterfactual Bias in LLMs
by: Chaudhary, Isha, et al.
Published: (2024)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
by: Xu, Yinglun, et al.
Published: (2024)

Cross-Input Certified Training for Universal Perturbations
by: Xu, Changming, et al.
Published: (2024)

Towards Generalized Certified Robustness with Multi-Norm Training
by: Jiang, Enyi, et al.
Published: (2024)

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models
by: Chu, Junjie, et al.
Published: (2024)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
by: Nikolić, Kristina, et al.
Published: (2025)

Certifying Knowledge Comprehension in LLMs
by: Chaudhary, Isha, et al.
Published: (2024)

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
by: Zhao, Mengnan, et al.
Published: (2026)

BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning
by: Liu, Yi, et al.
Published: (2024)

Certifying LLM Safety against Adversarial Prompting
by: Kumar, Aounon, et al.
Published: (2023)

Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning
by: Dou, Xuhui, et al.
Published: (2026)

Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities
by: Anurin, Andrey, et al.
Published: (2024)

PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks
by: Li, Xuran, et al.
Published: (2025)

FairProof : Confidential and Certifiable Fairness for Neural Networks
by: Yadav, Chhavi, et al.
Published: (2024)

How Not to Detect Prompt Injections with an LLM
by: Choudhary, Sarthak, et al.
Published: (2025)

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
by: Ponomareva, Natalia, et al.
Published: (2025)

Robust Privacy: Inference-Time Privacy through Certified Robustness
by: Jin, Jiankai, et al.
Published: (2026)

How to Backdoor the Knowledge Distillation
by: Wu, Chen, et al.
Published: (2025)

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
by: Huang, Tiansheng, et al.
Published: (2025)

Your Agent Can Defend Itself against Backdoor Attacks
by: Changjiang, Li, et al.
Published: (2025)

AuditVotes: A Framework Towards More Deployable Certified Robustness for Graph Neural Networks
by: Lai, Yuni, et al.
Published: (2025)

Q-AGNN: Quantum-Enhanced Attentive Graph Neural Network for Intrusion Detection
by: Chaudhary, Devashish, et al.
Published: (2026)

Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
by: Wu, Ruihan, et al.
Published: (2025)

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
by: Zafar, Osama, et al.
Published: (2026)

Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
by: Xu, Yijie, et al.
Published: (2025)

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
by: Zhang, Mohan, et al.
Published: (2025)

Formal Synthesis of Certifiably Robust Neural Lyapunov-Barrier Certificates
by: Wang, Chengxiao, et al.
Published: (2026)

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search
by: Luo, Zeren, et al.
Published: (2025)

How Private is Your Attention? Bridging Privacy with In-Context Learning
by: Bonnerjee, Soham, et al.
Published: (2025)

Uncertainty-Aware Hardware Trojan Detection Using Multimodal Deep Learning
by: Vishwakarma, Rahul, et al.
Published: (2024)

Protect Your Score: Contact Tracing With Differential Privacy Guarantees
by: Romijnders, Rob, et al.
Published: (2023)

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
by: Liang, Jiacheng, et al.
Published: (2026)

Your Privacy Depends on Others: Collusion Vulnerabilities in Individual Differential Privacy
by: Kaiser, Johannes, et al.
Published: (2026)

Matching Ranks Over Probability Yields Truly Deep Safety Alignment
by: Vega, Jason, et al.
Published: (2025)

How to Craft Backdoors with Unlabeled Data Alone?
by: Wang, Yifei, et al.
Published: (2024)

Is The Watermarking Of LLM-Generated Code Robust?
by: Suresh, Tarun, et al.
Published: (2024)

Do Phone-Use Agents Respect Your Privacy?
by: Tang, Zhengyang, et al.
Published: (2026)

Improving Your Model Ranking on Chatbot Arena by Vote Rigging
by: Min, Rui, et al.
Published: (2025)