Cover Image

Strategic Deflection: Defending LLMs from Logit Manipulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rachidy, Yassine, Rbaiti, Jihad, Hmamouche, Youssef, Sehbaoui, Faissal, Seghrouchni, Amal El Fallah
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VRWKV-Editor: Reducing quadratic complexity in transformer-based video editing
by: Aitrouga, Abdelilah, et al.
Published: (2025)

Constrained Network Adversarial Attacks: Validity, Robustness, and Transferability
by: Grini, Anass, et al.
Published: (2025)

Defend LLMs Through Self-Consciousness
by: Huang, Boshi, et al.
Published: (2025)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
by: Liu, Fan, et al.
Published: (2024)

SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking
by: Gu, Chenxi, et al.
Published: (2026)

Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
by: Lu, Guoxin, et al.
Published: (2026)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
by: Jiang, Peihai, et al.
Published: (2025)

Defending against Jailbreak through Early Exit Generation of Large Language Models
by: Zhao, Chongwen, et al.
Published: (2024)

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
by: Zhao, Shuai, et al.
Published: (2024)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
by: Xu, Zhangchen, et al.
Published: (2024)

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
by: Zhao, Jiawei, et al.
Published: (2024)

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization
by: Liu, Tiantian, et al.
Published: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
by: Jiang, Tanqiu, et al.
Published: (2024)

ForensicsData: A Digital Forensics Dataset for Large Language Models
by: Chakir, Youssef, et al.
Published: (2025)

HPAC-IDS: A Hierarchical Packet Attention Convolution for Intrusion Detection System
by: Grini, Anass, et al.
Published: (2025)

MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
by: Wang, Yuhao, et al.
Published: (2026)

A multimodal LLM for the non-invasive decoding of spoken text from brain recordings
by: Hmamouche, Youssef, et al.
Published: (2024)

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
by: Wang, Kai, et al.
Published: (2025)

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
by: Qian, Cheng, et al.
Published: (2024)

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
by: Cao, Bochuan, et al.
Published: (2023)

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
by: Kim, Jinhwa, et al.
Published: (2025)

MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
by: Jiang, Weisen, et al.
Published: (2025)

Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models
by: Chen, Zhuo, et al.
Published: (2024)

Protecting Your LLMs with Information Bottleneck
by: Liu, Zichuan, et al.
Published: (2024)

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
by: Sharma, Mrinank, et al.
Published: (2025)

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
by: Xu, Zhao, et al.
Published: (2024)

The Ethics of Interaction: Mitigating Security Threats in LLMs
by: Kumar, Ashutosh, et al.
Published: (2024)

PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
by: Pham, Viet, et al.
Published: (2025)

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

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
by: Jia, Feiran, et al.
Published: (2024)

LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
by: Hu, Xuhao, et al.
Published: (2025)

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
by: Wang, Xunguang, et al.
Published: (2024)

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
by: Akbar-Tajari, Mohammad, et al.
Published: (2025)

Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
by: Pu, Rui, et al.
Published: (2024)

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
by: Yang, Yan, et al.
Published: (2024)

Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs
by: Lau, Gregory Kang Ruey, et al.
Published: (2024)

bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
by: Ji, Wence, et al.
Published: (2025)

The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
by: Liu, Songyang, et al.
Published: (2025)

Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
by: Upadhayay, Bibek, et al.
Published: (2024)

Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
by: Hoang, Duy C., et al.
Published: (2024)