paper-with-me

홈 › Papers

When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection

2025-12-11 · Devanshu Sahoo, Manish Prasad, Vasudev Majhi, Jahnvi Singh, Vinay Chamola, Yash Sinha, Murari Mandal, Dhruv Kumar arxiv

Driven by surging submission volumes, scientific peer review has catalyzed two parallel trends: individual over-reliance on LLMs and institutional AI-powered assessment systems. This study investigates the robustness of "LLM-as-a-Judge" systems to adversarial PDF manipulation via invisible text injections and layout aware encoding attacks. We specifically target the distinct incentive of flipping "Reject" decisions to "Accept," a vulnerability that fundamentally compromises scientific integrity. To measure this, we introduce the Weighted Adversarial Vulnerability Score (WAVS), a novel metric that quantifies susceptibility by weighting score inflation against the severity of decision shifts relative to ground truth. We adapt 15 domain-specific attack strategies, ranging from semantic persuasion to cognitive obfuscation, and evaluate them across 13 diverse language models (including GPT-5 and DeepSeek) using a curated dataset of 200 official and real-world accepted and rejected submissions (e.g., ICLR OpenReview). Our results demonstrate that obfuscation techniques like "Maximum Mark Magyk" and "Symbolic Masking & Context Redirection" successfully manipulate scores, achieving decision flip rates of up to 86.26% in open-source models, while exposing distinct "reasoning traps" in proprietary systems. We release our complete dataset and injection framework to facilitate further research on the topic (https://anonymous.4open.sciencer/llm-jailbreak-FC9E/).

📄 PDF Abstract BibTeX arXiv:2512.10449

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments

2026-05-08 · Hanzaleh Akbari Nodehi, Parsa Moradi, Soheil Mohajer, Mohammad Ali Maddah-Ali arxiv

Decentralized machine learning often relies on outsourcing computations, such as gradient evaluations, to untrusted worker nodes. Existing robust aggregation methods can mitigate malicious behavior under honest-majority …

SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference

2026-07-03 · Huajun Bai, Weiwei Lv, Huichuan Zheng, Youyou Lu 외 arxiv

LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: the model reasons, emits a tool call, then idles the GPU until the resul…

Question Answering

Verification-Aware Training for Speculative Decoding

2026-08-31 · Geonmo Gu, Byeongho Heo, HeeJae Jun, Yoohoon Kang 외 arxiv

Speculative decoding accelerates large language model inference by using a draft model to generate candidate tokens, which are verified by the target model in a single forward pass. Verification proceeds sequentially and…

Broadening Label-based Argumentation Semantics with May-Must Scales (May-Must Argumentation)

2020-01-16 · Ryuta Arisaka, Takayuki Ito

The semantics as to which set of arguments in a given argumentation graph may be acceptable (acceptability semantics) can be characterised in a few different ways. Among them, labelling-based approach allows for concise …

Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms

2016-10-18 · Christian A. Naesseth, Francisco J. R. Ruiz, Scott W. Linderman, David M. Blei

Variational inference using the reparameterization trick has enabled large-scale approximate Bayesian inference in complex probabilistic models, leveraging stochastic optimization to sidestep intractable expectations. Th…

Bayesian InferenceStochastic OptimizationVariational Inference