paper-with-me

Papers

Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders & Researchers

2025-10-14 · Giacomo Bertollo, Naz Bodemir, Jonah Burgess arxiv

Analyzing 500 CTF participants, this paper shows that while participants readily bypassed simple AI guardrails using common techniques, layered multi-step defenses still posed significant challenges, offering concrete insights for building safer AI systems.

📄 PDF Abstract BibTeX arXiv:2510.16005

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models

2025-03-03 · Zhengyuan Jiang, Yuepeng Hu, Yuchen Yang, Yinzhi Cao 외

Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the…

Language ModelingLanguage ModellingLarge Language Model

Benchmarking LLM Guardrails in Handling Multilingual Toxicity

2024-10-29 · Yahan Yang, Soham Dan, Dan Roth, Insup Lee

With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiven…

Benchmarking

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection

2025-10-14 · Francesco Giarrusso, Olga E. Sorokoletova, Vincenzo Suriani, Daniele Nardi arxiv

Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across languages, and rely on limited taxonomies th…

SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models

2024-05-14 · Raghuveer Peri, Sai Muralidhar Jayanthi, Srikanth Ronanki, Anshu Bhatia 외

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largel…

Adversarial RobustnessInstruction FollowingQuestion Answering

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts

2025-07-01 · Annika M Schoene, Cansu Canca arxiv

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susce…