Image de couverture de livre

SafeSeek: Universal Attribution of Safety Circuits in Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Miao, Fu, Siyuan, Aloqaily, Moayad, Zhou, Zhenhong, Otoum, Safa, fan, Xing, Wang, Kun, Guo, Yufei, Wen, Qingsong
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
par: Yu, Miao, et autres
Publié: (2025)

Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
par: Lin, Liang, et autres
Publié: (2025)

MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
par: Zhou, Zhenhong, et autres
Publié: (2026)

ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
par: Luo, Kaiwen, et autres
Publié: (2026)

Editorial for the IJNM Special Issue From the Best Papers of IEEE ICBC 2023 “Advancing Blockchain and Cryptocurrency”
par: Laura Ricci, et autres
Publié: (2024)

HearSay Benchmark: Do Audio LLMs Leak What They Hear?
par: Wang, Jin, et autres
Publié: (2026)

Blockchain-enabled Energy Trading and Battery-based Sharing in Microgrids
par: Zekiye, Abdulrezzak, et autres
Publié: (2024)

ED-DAO: Energy Donation Algorithms based on Decentralized Autonomous Organization
par: Zekiye, Abdulrezzak, et autres
Publié: (2025)

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
par: Li, Zherui, et autres
Publié: (2025)

Generative AI for Networking
par: Zaman, Faisal, et autres
Publié: (2025)

Analysis of Blockchain Assisted Energy Sharing Algorithms with Realistic Data Across Microgrids
par: Zekiye, Abdulrezzak, et autres
Publié: (2024)

Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation
par: Zhang, Yuanhe, et autres
Publié: (2025)

NetSafe: Exploring the Topological Safety of Multi-agent Networks
par: Yu, Miao, et autres
Publié: (2024)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
par: Yu, Miao, et autres
Publié: (2024)

AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management
par: Mao, Junyuan, et autres
Publié: (2025)

Moderate deviation principle for the chi-square statistics
par: Yu, Zhenhong, et autres
Publié: (2025)

Some asymptotic behaviors for the plug-in estimator of entropy
par: Yu, Zhenhong, et autres
Publié: (2024)

Moderate deviation principle for plug-in estimators of diversity indices on countable alphabets
par: Yu, Zhenhong, et autres
Publié: (2025)

HomeSafeBench: A Benchmark for Embodied Vision-Language Models in Free-Exploration Home Safety Inspection
par: Gao, Siyuan, et autres
Publié: (2025)

SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
par: Ying, Zonghao, et autres
Publié: (2024)

Differential Privacy-Driven Framework for Enhancing Heart Disease Prediction
par: Otoum, Yazan, et autres
Publié: (2025)

On the Role of Attention Heads in Large Language Model Safety
par: Zhou, Zhenhong, et autres
Publié: (2024)

Safety Evaluation of DeepSeek Models in Chinese Contexts
par: Zhang, Wenjing, et autres
Publié: (2025)

Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts
par: Zhang, Wenjing, et autres
Publié: (2025)

Supersymmetric BMS$_4$ Algebras Revisited: Electric/Magnetic Superalgebras and Free Field Realization
par: Zheng, Yu-fan
Publié: (2025)

Large deviation inequalities for the nonlinear unbalanced urn model
par: Shi, Jianan, et autres
Publié: (2024)

Evaluator versus Target Characteristics: What Impacts Blame‐Attribution in Inter‐ and Intra‐ethnic Sexual Violence?
par: Safa Salim
Publié: (2025)

CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns
par: Zhou, Zhenhong, et autres
Publié: (2026)

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
par: Fu, Yu, et autres
Publié: (2023)

CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models
par: Zhang, Yiming, et autres
Publié: (2025)

UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models
par: Sun, Yuhao, et autres
Publié: (2025)

Driving Safety Prediction and Safe Route Mapping Using In-vehicle and Roadside Data
par: Huang, Yufei, et autres
Publié: (2022)

LLMs meet Federated Learning for Scalable and Secure IoT Management
par: Otoum, Yazan, et autres
Publié: (2025)

LLM-Based Threat Detection and Prevention Framework for IoT Ecosystems
par: Otoum, Yazan, et autres
Publié: (2025)

Blockchain Meets Adaptive Honeypots: A Trust-Aware Approach to Next-Gen IoT Security
par: Otoum, Yazan, et autres
Publié: (2025)

Open-Source LLM-Driven Federated Transformer for Predictive IoV Management
par: Otoum, Yazan, et autres
Publié: (2025)

SafeMT: Multi-turn Safety for Multimodal Language Models
par: Zhu, Han, et autres
Publié: (2025)

Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
par: Zhou, Zhenhong, et autres
Publié: (2024)

Structure of Carrollian (conformal) superalgebra
par: Zheng, Yu-fan, et autres
Publié: (2025)

Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models
par: Ahmadi, Saba, et autres
Publié: (2026)