paper-with-me

홈 › Papers

Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

2023-05-24 · Abhinav Rao, Sachin Vashistha, Atharva Naik, Somak Aditya, Monojit Choudhury

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive outputs, and violations of content regulator policies. Limited studies have been conducted to formalize and analyze these attacks and their mitigations. We bridge this gap by proposing a formalism and a taxonomy of known (and possible) jailbreaks. We survey existing jailbreak methods and their effectiveness on open-source and commercial LLMs (such as GPT-based models, OPT, BLOOM, and FLAN-T5-XXL). We further discuss the challenges of jailbreak detection in terms of their effectiveness against known attacks. For further analysis, we release a dataset of model outputs across 3700 jailbreak prompts over 4 tasks.

📄 PDF Abstract BibTeX arXiv:2305.14965

Code (1)

AetherPrior/TrickLLM 공식 구현

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Weight Decay 설명 없음
Residual Connection 설명 없음
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Similar Papers 제목 키워드 기반

Rebellion and Disobedience as Useful Tools in Human-Robot Interaction Research -- The Handheld Robotics Case

2022-05-08 · Walterio W. Mayol-Cuevas

This position paper argues on the utility of rebellion and disobedience (RaD) in human-robot interaction (HRI). In general, we see two main opportunities in the use of controlled and well designed rebellion and disobedie…

Position

The Intelligent Disobedience Game: Formulating Disobedience in Stackelberg Games and Markov Decision Processes

2026-03-22 · Benedikt Hornig, Reuth Mirsky arxiv

In shared autonomy, a critical tension arises when an automated assistant must choose between obeying a human's instruction and deliberately overriding it to prevent harm. This safety-critical behavior is known as intell…

Reinforcement Learning

Tricking LLM-Based NPCs into Spilling Secrets

2025-08-25 · Kyohei Shiomi, Zhuotao Lian, Toru Nakanishi, Teruaki Kitasuka arxiv

Large Language Models (LLMs) are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can c…

Formalizing Complex Mathematical Statements with LLMs: A Study on Mathematical Definitions

2025-02-17 · Lan Zhang, Marco Valentino, Andre Freitas

Thanks to their linguistic capabilities, LLMs offer an opportunity to bridge the gap between informal mathematics and formal languages through autoformalization. However, it is still unclear how well LLMs generalize to s…

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

2026-09-14 · Aashiq Muhamed, Mona T. Diab, Virginia Smith hf

Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and projects out a linear refusal direction from the residual stream, often achie…