Copertina

The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Berezin, Sergey, Farahbakhsh, Reza, Crespi, Noel
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems
di: Berezin, Sergey, et al.
Pubblicazione: (2024)

Toxicity Detection Should Measure Contextual Harm, Not Text-Intrinsic Badness
di: Berezin, Sergei, et al.
Pubblicazione: (2025)

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

Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models
di: Liu, Xiao, et al.
Pubblicazione: (2024)

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
di: Kirch, Nathalie, et al.
Pubblicazione: (2024)

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
di: Fastowski, Alina, et al.
Pubblicazione: (2025)

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
di: Paulus, Anselm, et al.
Pubblicazione: (2024)

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

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
di: Shao, Zedian, et al.
Pubblicazione: (2024)

Adversarial Attacks Against Automated Fact-Checking: A Survey
di: Liu, Fanzhen, et al.
Pubblicazione: (2025)

Fast Adversarial Attacks on Language Models In One GPU Minute
di: Sadasivan, Vinu Sankar, et al.
Pubblicazione: (2024)

Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework
di: Pisano, Matthew, et al.
Pubblicazione: (2023)

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

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
di: Zheng, Yujia, et al.
Pubblicazione: (2025)

Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations
di: Teja, Lekkala Sai, et al.
Pubblicazione: (2025)

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

Jatmo: Prompt Injection Defense by Task-Specific Finetuning
di: Piet, Julien, et al.
Pubblicazione: (2023)

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
di: Jang, Yeonwoo, et al.
Pubblicazione: (2025)

Goal-guided Generative Prompt Injection Attack on Large Language Models
di: Zhang, Chong, et al.
Pubblicazione: (2024)

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
di: Li, Xirui, et al.
Pubblicazione: (2024)

What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
di: Weiss, Roy, et al.
Pubblicazione: (2024)

WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
di: Wang, Xilong, et al.
Pubblicazione: (2026)

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

Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization
di: Cooper, Portia, et al.
Pubblicazione: (2024)

Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks
di: Aldahoul, Nouar, et al.
Pubblicazione: (2025)

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
di: Ostermann, Simon, et al.
Pubblicazione: (2024)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
di: Li, Hao, et al.
Pubblicazione: (2026)

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

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

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

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
di: Zhao, Shuai, et al.
Pubblicazione: (2024)

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
di: Hu, Xiaomeng, et al.
Pubblicazione: (2025)

ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs
di: Ni, Ziyi, et al.
Pubblicazione: (2025)

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

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
di: Wei, Jiali, et al.
Pubblicazione: (2026)

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
di: Schwartz, Daniel, et al.
Pubblicazione: (2025)

LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation
di: Li, Xingyu, et al.
Pubblicazione: (2025)

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
di: Xu, Naen, et al.
Pubblicazione: (2026)

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
di: Yan, Dong, et al.
Pubblicazione: (2026)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
di: Cheng, Pengzhou, et al.
Pubblicazione: (2024)