Buchumschlag

Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Xiaomei, Zhang, Zhaoxi, Zhang, Yanjun, Zheng, Xufei, Zhang, Leo Yu, Hu, Shengshan, Pan, Shirui
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language Artificial Intelligence Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

Large Language Model Watermark Stealing With Mixed Integer Programming
von: Zhang, Zhaoxi, et al.
Veröffentlicht: (2024)

Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models
von: Zhang, Xiaomei, et al.
Veröffentlicht: (2026)

BiMark: Unbiased Multilayer Watermarking for Large Language Models
von: Feng, Xiaoyan, et al.
Veröffentlicht: (2025)

Character-Level Perturbations Disrupt LLM Watermarks
von: Zhang, Zhaoxi, et al.
Veröffentlicht: (2025)

SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack
von: Liu, Han, et al.
Veröffentlicht: (2026)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
von: Mu, Junjie, et al.
Veröffentlicht: (2025)

Fast Adversarial Training against Textual Adversarial Attacks
von: Yang, Yichen, et al.
Veröffentlicht: (2024)

Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks
von: Lin, Tzu-Ling, et al.
Veröffentlicht: (2025)

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
von: Hu, Xiaomeng, et al.
Veröffentlicht: (2024)

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
von: Liu, Han, et al.
Veröffentlicht: (2024)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
von: Yu, Miao, et al.
Veröffentlicht: (2024)

ELAD: Explanation-Guided Large Language Models Active Distillation
von: Zhang, Yifei, et al.
Veröffentlicht: (2024)

Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning
von: Zhuo, Xingrui, et al.
Veröffentlicht: (2025)

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
von: Song, Yufei, et al.
Veröffentlicht: (2024)

Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences
von: Zhang, Yangshijie
Veröffentlicht: (2025)

Claim-Guided Textual Backdoor Attack for Practical Applications
von: Song, Minkyoo, et al.
Veröffentlicht: (2024)

Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend
von: Lu, Ning, et al.
Veröffentlicht: (2023)

SynDec: A Synthesize-then-Decode Approach for Arbitrary Textual Style Transfer via Large Language Models
von: Sun, Han, et al.
Veröffentlicht: (2025)

TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
von: Li, Zhuofeng, et al.
Veröffentlicht: (2024)

Fine-tuning Language Models with Generative Adversarial Reward Modelling
von: Yu, Zhang Ze, et al.
Veröffentlicht: (2023)

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
von: Wang, Chenyu, et al.
Veröffentlicht: (2025)

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
von: Luo, Linhao, et al.
Veröffentlicht: (2023)

A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents
von: Mo, Lingbo, et al.
Veröffentlicht: (2024)

When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning
von: Sun, Ruining, et al.
Veröffentlicht: (2025)

SuperMerge: An Approach For Gradient-Based Model Merging
von: Yang, Haoyu, et al.
Veröffentlicht: (2024)

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
von: Lin, Huawei, et al.
Veröffentlicht: (2025)

Abstraction-of-Thought Makes Language Models Better Reasoners
von: Hong, Ruixin, et al.
Veröffentlicht: (2024)

Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
von: Su, Zhenpeng, et al.
Veröffentlicht: (2023)

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills
von: Liu, Yi, et al.
Veröffentlicht: (2026)

Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
von: Zheng, Kaiwen, et al.
Veröffentlicht: (2024)

Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning
von: Liu, Yu, et al.
Veröffentlicht: (2025)

Boosting Large Language Models with Mask Fine-Tuning
von: Zhang, Mingyuan, et al.
Veröffentlicht: (2025)

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
von: Amayuelas, Alfonso, et al.
Veröffentlicht: (2024)

SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
von: Qu, Yubin, et al.
Veröffentlicht: (2026)

Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models
von: Jia, Boyu, et al.
Veröffentlicht: (2025)

Integrating Large Language Models and Knowledge Graphs for Extraction and Validation of Textual Test Data
von: De Santis, Antonio, et al.
Veröffentlicht: (2024)

Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning
von: Zhao, Jun, et al.
Veröffentlicht: (2024)

Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining
von: Guo, Ping, et al.
Veröffentlicht: (2025)

$\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models
von: Ju, Jiaxin, et al.
Veröffentlicht: (2025)