paper-with-me

Papers

Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt Injections

2025-04-25 · Narek Maloyan, Dmitry Namiot

LLM as judge systems used to assess text quality code correctness and argument strength are vulnerable to prompt injection attacks. We introduce a framework that separates content author attacks from system prompt attacks and evaluate five models Gemma 3.27B Gemma 3.4B Llama 3.2 3B GPT 4 and Claude 3 Opus on four tasks with various defenses using fifty prompts per condition. Attacks achieved up to seventy three point eight percent success smaller models proved more vulnerable and transferability ranged from fifty point five to sixty two point six percent. Our results contrast with Universal Prompt Injection and AdvPrompter We recommend multi model committees and comparative scoring and release all code and datasets

📄 PDF Abstract BibTeX arXiv:2504.18333

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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 &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models

2026-03-26 · Hieu Xuan Le, Benjamin Goh, Quy Anh Tang arxiv

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints,…

Red Teaming

Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks

2025-05-19 · Narek Maloyan, Bislan Ashinov, Dmitry Namiot

Large Language Models (LLMs) are increasingly employed as evaluators (LLM-as-a-Judge) for assessing the quality of machine-generated text. This paradigm offers scalability and cost-effectiveness compared to human annotat…

CourtGuard: A Local, Multiagent Prompt Injection Classifier

2025-10-20 · Isaac Wu, Michael Maslowski arxiv

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks…

Adversarially Robust Neural Legal Judgement Systems

2023-07-31 · Rohit Raj, V Susheela Devi

Legal judgment prediction is the task of predicting the outcome of court cases on a given text description of facts of cases. These tasks apply Natural Language Processing (NLP) techniques to predict legal judgment resul…

Prediction

Measuring the Robustness of Reference-Free Dialogue Evaluation Systems

2025-01-12 · Justin Vasselli, Adam Nohejl, Taro Watanabe

Advancements in dialogue systems powered by large language models (LLMs) have outpaced the development of reliable evaluation metrics, particularly for diverse and creative responses. We present a benchmark for evaluatin…

Dialogue EvaluationTAG