Copertina

OverThink: Slowdown Attacks on Reasoning LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kumar, Abhinav, Roh, Jaechul, Naseh, Ali, Karpinska, Marzena, Iyyer, Mohit, Houmansadr, Amir, Bagdasarian, Eugene
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Throttling Web Agents Using Reasoning Gates
di: Kumar, Abhinav, et al.
Pubblicazione: (2025)

Backdooring Bias ($B^2$) into Stable Diffusion Models
di: Naseh, Ali, et al.
Pubblicazione: (2024)

OSLO: One-Shot Label-Only Membership Inference Attacks
di: Peng, Yuefeng, et al.
Pubblicazione: (2024)

R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model
di: Naseh, Ali, et al.
Pubblicazione: (2025)

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
di: Roh, Jaechul, et al.
Pubblicazione: (2026)

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images
di: Naseh, Ali, et al.
Pubblicazione: (2024)

Diffence: Fencing Membership Privacy With Diffusion Models
di: Peng, Yuefeng, et al.
Pubblicazione: (2023)

Multilingual and Multi-Accent Jailbreaking of Audio LLMs
di: Roh, Jaechul, et al.
Pubblicazione: (2025)

PostMark: A Robust Blackbox Watermark for Large Language Models
di: Chang, Yapei, et al.
Pubblicazione: (2024)

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
di: Naseh, Ali, et al.
Pubblicazione: (2025)

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
di: Suri, Anshuman, et al.
Pubblicazione: (2025)

Network-Level Prompt and Trait Leakage in Local Research Agents
di: Jeong, Hyejun, et al.
Pubblicazione: (2025)

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation
di: Pham, Dzung, et al.
Pubblicazione: (2023)

FameBias: Embedding Manipulation Bias Attack in Text-to-Image Models
di: Roh, Jaechul, et al.
Pubblicazione: (2024)

Identifying Models Behind Text-to-Image Leaderboards
di: Naseh, Ali, et al.
Pubblicazione: (2026)

Contextual Agent Security: A Policy for Every Purpose
di: Tsai, Lillian, et al.
Pubblicazione: (2025)

Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
di: Mozaffari, Hamid, et al.
Pubblicazione: (2024)

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
di: Naseh, Ali, et al.
Pubblicazione: (2025)

Excessive Reasoning Attack on Reasoning LLMs
di: Si, Wai Man, et al.
Pubblicazione: (2025)

Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
di: Naseh, Ali, et al.
Pubblicazione: (2025)

Persistent Backdoor Attacks in Continual Learning
di: Guo, Zhen, et al.
Pubblicazione: (2024)

Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation
di: Roh, Jaechul, et al.
Pubblicazione: (2025)

Can Large Language Models Really Recognize Your Name?
di: Pham, Dzung, et al.
Pubblicazione: (2025)

Self-interpreting Adversarial Images
di: Zhang, Tingwei, et al.
Pubblicazione: (2024)

VIDSTAMP: A Temporally-Aware Watermark for Ownership and Integrity in Video Diffusion Models
di: Teymoorianfard, Mohammadreza, et al.
Pubblicazione: (2025)

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
di: Amini, Sajjad, et al.
Pubblicazione: (2024)

FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs
di: Meerza, Syed Irfan Ali, et al.
Pubblicazione: (2026)

Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography
di: Shumailov, Ilia, et al.
Pubblicazione: (2025)

Efficient Adversarial Training in LLMs with Continuous Attacks
di: Xhonneux, Sophie, et al.
Pubblicazione: (2024)

Instruction Backdoor Attacks Against Customized LLMs
di: Zhang, Rui, et al.
Pubblicazione: (2024)

AirGapAgent: Protecting Privacy-Conscious Conversational Agents
di: Bagdasarian, Eugene, et al.
Pubblicazione: (2024)

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks
di: Dong, Xuewen, et al.
Pubblicazione: (2025)

Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks
di: Eykholt, Kevin, et al.
Pubblicazione: (2024)

Membership Inference Attacks on Vision-Language-Action Models
di: Peng, Yuefeng, et al.
Pubblicazione: (2026)

Towards Automatic Hands-on-Keyboard Attack Detection Using LLMs in EDR Solutions
di: Portnoy, Amit, et al.
Pubblicazione: (2024)

An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs
di: Thomas, Rahul, et al.
Pubblicazione: (2025)

Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemble
di: Liu, Dancheng, et al.
Pubblicazione: (2024)

Guided Reasoning in LLM-Driven Penetration Testing Using Structured Attack Trees
di: Nakano, Katsuaki, et al.
Pubblicazione: (2025)

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
di: Chaudhari, Harsh, et al.
Pubblicazione: (2026)

Linkage Attacks Expose Identity Risks in Public ECG Data Sharing
di: Wang, Ziyu, et al.
Pubblicazione: (2025)