Copertina

Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mo, Wenjie, Xu, Jiashu, Liu, Qin, Wang, Jiongxiao, Yan, Jun, Askari, Hadi, Xiao, Chaowei, Chen, Muhao
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges
di: Liu, Qin, et al.
Pubblicazione: (2024)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
di: Xu, Jiashu, et al.
Pubblicazione: (2023)

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
di: Liu, Qin, et al.
Pubblicazione: (2023)

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
di: Wang, Jiongxiao, et al.
Pubblicazione: (2023)

FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
di: Wang, Jiongxiao, et al.
Pubblicazione: (2024)

Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
di: Tong, Terry, et al.
Pubblicazione: (2024)

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
di: Wang, Jiongxiao, et al.
Pubblicazione: (2024)

Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
di: Nahin, Shahriar Kabir, et al.
Pubblicazione: (2025)

Instructional Fingerprinting of Large Language Models
di: Xu, Jiashu, et al.
Pubblicazione: (2024)

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
di: Liu, Xiaogeng, et al.
Pubblicazione: (2023)

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
di: Askari, Hadi, et al.
Pubblicazione: (2025)

Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
di: Graf, Victoria, et al.
Pubblicazione: (2024)

Rethinking Backdoor Detection Evaluation for Language Models
di: Yan, Jun, et al.
Pubblicazione: (2024)

Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing
di: Askari, Hadi, et al.
Pubblicazione: (2024)

Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
di: Xu, Nan, et al.
Pubblicazione: (2023)

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
di: Li, Yu, et al.
Pubblicazione: (2026)

SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
di: Liu, Qin, et al.
Pubblicazione: (2024)

SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening
di: Nahin, Shahriar Kabir, et al.
Pubblicazione: (2026)

DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning
di: Qiu, Hongye, et al.
Pubblicazione: (2025)

Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias
di: Chhabra, Anshuman, et al.
Pubblicazione: (2024)

Preference Poisoning Attacks on Reward Model Learning
di: Wu, Junlin, et al.
Pubblicazione: (2024)

Knowledge Distillation of Black-Box Large Language Models
di: Chen, Hongzhan, et al.
Pubblicazione: (2024)

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
di: Zhao, Shuai, et al.
Pubblicazione: (2024)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
di: Yi, Biao, et al.
Pubblicazione: (2025)

How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities
di: Mo, Lingbo, et al.
Pubblicazione: (2023)

Multilingual Collaborative Defense for Large Language Models
di: Li, Hongliang, et al.
Pubblicazione: (2025)

ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
di: Wang, Xinyan, et al.
Pubblicazione: (2026)

Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations
di: Salimian, Sina, et al.
Pubblicazione: (2025)

Monotonic Paraphrasing Improves Generalization of Language Model Prompting
di: Liu, Qin, et al.
Pubblicazione: (2024)

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
di: Cheng, Jiale, et al.
Pubblicazione: (2023)

AJF: Adaptive Jailbreak Framework Based on the Comprehension Ability of Black-Box Large Language Models
di: Yu, Mingyu, et al.
Pubblicazione: (2025)

DebugLM: Learning Traceable Training Data Provenance for LLMs
di: Mo, Wenjie Jacky, et al.
Pubblicazione: (2026)

Black-Box On-Policy Distillation of Large Language Models
di: Ye, Tianzhu, et al.
Pubblicazione: (2025)

Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models
di: Woo, Sangmin, et al.
Pubblicazione: (2025)

Beyond the Black Box: A Survey on the Theory and Mechanism of Large Language Models
di: Gan, Zeyu, et al.
Pubblicazione: (2026)

VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
di: Liu, Qin, et al.
Pubblicazione: (2025)

RPM: Reasoning-Level Personalization for Black-Box Large Language Models
di: Kim, Jieyong, et al.
Pubblicazione: (2025)

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models
di: Zhu, Tinghui, et al.
Pubblicazione: (2024)

Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models
di: Xu, Yue, et al.
Pubblicazione: (2024)

ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails
di: Wen, Xiaofei, et al.
Pubblicazione: (2025)