This work proposes two classes of attacks: a static attack, which employs a fixed injection prompt, and an iterative attack, which optimizes the injection prompt against a simulated reviewer model to maximize its effectiveness.
Abstract
With the rapid advancement of AI models, their deployment across diverse tasks has become increasingly widespread. A notable emerging application is leveraging AI models to assist in reviewing scientific papers. However, recent reports have revealed that some papers contain hidden, injected prompts designed to manipulate AI reviewers into providing overly favorable evaluations. In this work, we present an early systematic investigation into this emerging threat. We propose two classes of attacks: (1) static attack, which employs a fixed injection prompt, and (2) iterative attack, which optimizes the injection prompt against a simulated reviewer model to maximize its effectiveness. Both attacks achieve striking performance, frequently inducing full evaluation scores when targeting frontier AI reviewers. Furthermore, we show that these attacks are robust across various settings. To counter this threat, we explore a simple detection-based defense. While it substantially reduces the attack success rate, we demonstrate that an adaptive attacker can partially circumvent this defense. Our findings underscore the need for greater attention and rigorous safeguards against prompt-injection threats in AI-assisted peer review.
Aligned RAG Evaluation is introduced, a matched-query protocol that jointly examines clean and poisoned responses, with and without defense, and exposes critical blind spots in ASR-based evaluation and motivates a more comprehensive assessment of RAG poisoning defenses.
Pull-request review protects software before new code reaches users, helping prevent vulnerabilities that could expose users to attacks. AI agents increasingly perform these reviews and explain which problems need fixing. However, for an attacker submitting vulnerable code, this feedback also reveals what changes may s...
Jing-Zhi Gong, Jie M. Zhang, Gunel Jahangirova et al.· 1 citation
CoDeL is presented, a defense that hardens agent against an attack distribution it reshapes as it trains, and reduces attack success rate (ASR) by 88.5% and outperforms other baselines largely (+38.0%).
Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pikit, a research toolkit designed to systematically evaluate these threats across three core dimensions: attacks (13 methods), channels (16 ca...
Zong-Hao Ying, Xiang-Fan Wu, Bo Yang et al.· arXiv.org· 0 citations
Prompt injection is usually discussed and evaluated as a single, homogeneous type of attack. However, vulnerabilities reported in real-world systems show that prompt injections vary widely. Moreover, the same instruction can be a prompt injection in one context and a legitimate request in another, depending on the user...
Jia-Min Chang, Kristina Nikolic, Rishi Sharma et al.· 0 citations
Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls. Benchmarks measure IPI security by the attack success rate (ASR), which treats every failed attack as a successful defense. To test this assumption, we audit...
Farhan Zarif, Kazi Shahid Ahmed Galib, Synthia Akter Promi et al.· 1 citation
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.