Cover Image

State-Dependent Safety Failures in Multi-Turn Language Model Interaction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Pengcheng, Zhang, Jie, Zhang, Tianwei, Qiu, Han, kejun, Zhang, Zhang, Weiming, Yu, Nenghai, Zhou, Wenbo
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
by: Su, Yanghao, et al.
Published: (2026)

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
by: Qi, Peigui, et al.
Published: (2025)

A high-capacity linguistic steganography based on entropy-driven rank-token mapping
by: Jiang, Jun, et al.
Published: (2025)

Provably Secure Agent Guardrail
by: Wu, Benlong, et al.
Published: (2026)

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
by: Ou, Haoran, et al.
Published: (2025)

BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
by: Yan, Xiaobei, et al.
Published: (2025)

An Engorgio Prompt Makes Large Language Model Babble on
by: Dong, Jianshuo, et al.
Published: (2024)

Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection
by: Li, Shuai, et al.
Published: (2023)

InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model
by: Tong, Meng, et al.
Published: (2023)

ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
by: Li, Guanlin, et al.
Published: (2024)

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
by: Feng, Weitao, et al.
Published: (2024)

Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks
by: Liu, Chang, et al.
Published: (2025)

AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?
by: Wu, Benlong, et al.
Published: (2024)

©Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model
by: Zhou, Chao, et al.
Published: (2024)

Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
by: Yang, Xianglin, et al.
Published: (2025)

BURN: Backdoor Unlearning via Adversarial Boundary Analysis
by: Su, Yanghao, et al.
Published: (2025)

Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models
by: Zhang, Jie, et al.
Published: (2024)

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
by: Chen, Yulong, et al.
Published: (2025)

Model X-ray:Detecting Backdoored Models via Decision Boundary
by: Su, Yanghao, et al.
Published: (2024)

AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
by: Song, Weiming, et al.
Published: (2026)

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
by: Chen, Meng, et al.
Published: (2026)

Membership Inference Attacks on Tokenizers of Large Language Models
by: Tong, Meng, et al.
Published: (2025)

Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
by: Rayhan, Naheed, et al.
Published: (2026)

SQL Injection Jailbreak: A Structural Disaster of Large Language Models
by: Zhao, Jiawei, et al.
Published: (2024)

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
by: Ying, Zonghao, et al.
Published: (2025)

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
by: Yang, Xianglin, et al.
Published: (2026)

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
by: Chen, Kejia, et al.
Published: (2026)

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
by: Zhang, Xinkai, et al.
Published: (2026)

LeakDojo: Decoding the Leakage Threats of RAG Systems
by: Zhang, Maosen, et al.
Published: (2026)

Safety Layers in Aligned Large Language Models: The Key to LLM Security
by: Li, Shen, et al.
Published: (2024)

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
by: Wang, Kun, et al.
Published: (2026)

DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
by: Ou, Haoran, et al.
Published: (2026)

PoseGuard: Pose-Guided Generation with Safety Guardrails
by: Wang, Kongxin, et al.
Published: (2025)

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
by: Zheng, Baolin, et al.
Published: (2025)

De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
by: Fan, Wei, et al.
Published: (2025)

WavInWav: Time-domain Speech Hiding via Invertible Neural Network
by: Fan, Wei, et al.
Published: (2025)

Fluent: Round-efficient Secure Aggregation for Private Federated Learning
by: Li, Xincheng, et al.
Published: (2024)

Masked Language Model Based Textual Adversarial Example Detection
by: Zhang, Xiaomei, et al.
Published: (2023)

MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
by: Guo, Weiyang, et al.
Published: (2025)

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
by: Wang, Youze, et al.
Published: (2025)