Cover Image

BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Fengqing, Feng, Yichen, Li, Yuetai, Niu, Luyao, Alomair, Basel, Poovendran, Radha
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
by: Li, Yuetai, et al.
Published: (2024)

ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
by: Jiang, Fengqing, et al.
Published: (2024)

Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning
by: Xu, Zhangchen, et al.
Published: (2024)

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
by: Xiang, Zhen, et al.
Published: (2024)

ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
by: Xu, Zhangchen, et al.
Published: (2024)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
by: Xu, Zhangchen, et al.
Published: (2024)

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
by: Jiang, Fengqing, et al.
Published: (2025)

The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
by: Jiang, Fengqing, et al.
Published: (2026)

Polyhedral Instability Governs Regret in Online Learning
by: Li, Yuetai, et al.
Published: (2026)

Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
by: Sahabandu, Dinuka, et al.
Published: (2024)

Defending Against Prompt Injection with DataFilter
by: Wang, Yizhu, et al.
Published: (2025)

PromptShield: Deployable Detection for Prompt Injection Attacks
by: Jacob, Dennis, et al.
Published: (2025)

Preventing Prompt Injection with Type-Directed Privilege Separation
by: Jacob, Dennis, et al.
Published: (2025)

CANTXSec: A Deterministic Intrusion Detection and Prevention System for CAN Bus Monitoring ECU Activations
by: Donadel, Denis, et al.
Published: (2025)

SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing
by: Wen, Aidan, et al.
Published: (2025)

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
by: Abdali, Sara, et al.
Published: (2024)

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
by: Piet, Julien, et al.
Published: (2025)

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
by: Abdelnabi, Sahar, et al.
Published: (2026)

Writing a Good Security Paper for ISSCC (2025)
by: Banerjee, Utsav, et al.
Published: (2025)

Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization
by: Rajabi, Arezoo, et al.
Published: (2024)

Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy
by: Jeong, Joonhyun, et al.
Published: (2025)

Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis
by: Thornton, Scott
Published: (2026)

Jatmo: Prompt Injection Defense by Task-Specific Finetuning
by: Piet, Julien, et al.
Published: (2023)

StyleFool: Fooling Video Classification Systems via Style Transfer
by: Cao, Yuxin, et al.
Published: (2022)

No More Hidden Pitfalls? Exposing Smart Contract Bad Practices with LLM-Powered Hybrid Analysis
by: Li, Xiaoqi, et al.
Published: (2025)

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
by: Wang, Yifei, et al.
Published: (2024)

Deep-Research Agents Can Be Poisoned via User-Generated Content
by: Zhang, Tingwei, et al.
Published: (2026)

Can Agents Secure Hardware? Evaluating Agentic LLM-Driven Obfuscation for IP Protection
by: Ghimire, Sujan, et al.
Published: (2026)

Dynamic Deception: When Pedestrians Team Up to Fool Autonomous Cars
by: Tehrani, Masoud Jamshidiyan, et al.
Published: (2026)

BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator
by: Zhang, Ruyi, et al.
Published: (2026)

TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
by: Xu, Zhangchen, et al.
Published: (2025)

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks
by: Qraitem, Maan, et al.
Published: (2024)

When and How to Fool Explainable Models (and Humans) with Adversarial Examples
by: Vadillo, Jon, et al.
Published: (2021)

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL
by: Feng, Yichen, et al.
Published: (2025)

Bad Crypto: Chessography and Weak Randomness of Chess Games
by: Stanek, Martin
Published: (2024)

Fooling SHAP with Output Shuffling Attacks
by: Yuan, Jun, et al.
Published: (2024)

Revisiting DeepFool: generalization and improvement
by: Abdollahpoorrostam, Alireza, et al.
Published: (2023)

Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perception
by: McKee, Forrest, et al.
Published: (2024)

Paper Agents, Paper Gains: An Empirical Analysis of DeFi Investment Agents
by: Yu, Jay, et al.
Published: (2026)

Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-Coded Credentials
by: Huang, Yizhan, et al.
Published: (2023)