Image de couverture de livre

Defend LLMs Through Self-Consciousness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Boshi, de Paula, Fabio Nonato
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computation and Language Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Strategic Deflection: Defending LLMs from Logit Manipulation
par: Rachidy, Yassine, et autres
Publié: (2025)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
par: Liu, Fan, et autres
Publié: (2024)

Defending against Jailbreak through Early Exit Generation of Large Language Models
par: Zhao, Chongwen, et autres
Publié: (2024)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
par: Jiang, Peihai, et autres
Publié: (2025)

Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
par: Lu, Guoxin, et autres
Publié: (2026)

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
par: Zhao, Shuai, et autres
Publié: (2024)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
par: Xu, Zhangchen, et autres
Publié: (2024)

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
par: Zhao, Jiawei, et autres
Publié: (2024)

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization
par: Liu, Tiantian, et autres
Publié: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
par: Jiang, Tanqiu, et autres
Publié: (2024)

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
par: Wang, Xunguang, et autres
Publié: (2024)

MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
par: Wang, Yuhao, et autres
Publié: (2026)

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
par: Qian, Cheng, et autres
Publié: (2024)

The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
par: Liu, Songyang, et autres
Publié: (2025)

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
par: Yang, Yan, et autres
Publié: (2024)

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
par: Cao, Bochuan, et autres
Publié: (2023)

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
par: Kim, Jinhwa, et autres
Publié: (2025)

LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
par: Hu, Xuhao, et autres
Publié: (2025)

MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
par: Jiang, Weisen, et autres
Publié: (2025)

Protecting Your LLMs with Information Bottleneck
par: Liu, Zichuan, et autres
Publié: (2024)

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
par: Sharma, Mrinank, et autres
Publié: (2025)

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
par: Xu, Zhao, et autres
Publié: (2024)

The Ethics of Interaction: Mitigating Security Threats in LLMs
par: Kumar, Ashutosh, et autres
Publié: (2024)

Jailbreaking Large Language Models Through Content Concretization
par: Wahréus, Johan, et autres
Publié: (2025)

Jailbreaking Frontier Foundation Models Through Intention Deception
par: Wang, Xinhe, et autres
Publié: (2026)

PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
par: Pham, Viet, et autres
Publié: (2025)

BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems
par: Zhang, Andy K., et autres
Publié: (2025)

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
par: Jia, Feiran, et autres
Publié: (2024)

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
par: Akbar-Tajari, Mohammad, et autres
Publié: (2025)

bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
par: Ji, Wence, et autres
Publié: (2025)

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
par: Liu, Jinbo, et autres
Publié: (2025)

Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
par: Pu, Rui, et autres
Publié: (2024)

Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs
par: Lau, Gregory Kang Ruey, et autres
Publié: (2024)

Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
par: Upadhayay, Bibek, et autres
Publié: (2024)

Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
par: Hoang, Duy C., et autres
Publié: (2024)

Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
par: Shen, Guangyu, et autres
Publié: (2024)

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
par: Zhao, Shuai, et autres
Publié: (2024)

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
par: Hu, Xiaomeng, et autres
Publié: (2025)

ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs
par: Ni, Ziyi, et autres
Publié: (2025)

Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks
par: Gohil, Vasudev
Publié: (2025)