Philipp Zimmermann
← Back to Newsletter

Paper Library

Collection of AI Security research papers

Showing 947 papers total

December 01 - December 07, 2025

7 papers

DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses

Han Luo, Guy Laban
2025-12-01
safety
2512.02282v1

Ensemble Privacy Defense for Knowledge-Intensive LLMs against Membership Inference Attacks

Haowei Fu, Bo Ni, Han Xu, Kunpeng Liu, Dan Lin, Tyler Derr
2025-12-01
safety
2512.03100v1

GRASP: Guided Residual Adapters with Sample-wise Partitioning

Felix Nützel, Mischa Dombrowski, Bernhard Kainz
2025-12-01
2512.01675v1

The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search

Rongzhe Wei, Peizhi Niu, Xinjie Shen, Tony Tu, Yifan Li, Ruihan Wu, Eli Chien, Pin-Yu Chen, Olgica Milenkovic, Pan Li
2025-12-01
red teaming
2512.01353v2

A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search

Rongzhe Wei, Peizhi Niu, Xinjie Shen, Tony Tu, Yifan Li, Ruihan Wu, Eli Chien, Olgica Milenkovic, Pan Li
2025-12-01
red teaming
2512.01353v1

Securing Large Language Models (LLMs) from Prompt Injection Attacks

Omar Farooq Khan Suri, John McCrae
2025-12-01
red teaming
2512.01326v1

DefenSee: Dissecting Threat from Sight and Text - A Multi-View Defensive Pipeline for Multi-modal Jailbreaks

Zihao Wang, Kar Wai Fok, Vrizlynn L. L. Thing
2025-12-01
2512.01185v1

November 24 - November 30, 2025

17 papers

When Safety Blocks Sense: Measuring Semantic Confusion in LLM Refusals

Riad Ahmed Anonto, Md Labid Al Nahiyan, Md Tanvir Hassan, Ch. Md. Rakin Haider
2025-11-30
safety
2512.01037v1

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis

Mintong Kang, Chong Xiang, Sanjay Kariyappa, Chaowei Xiao, Bo Li, Edward Suh
2025-11-30
red teaming
2512.00966v1

On the Regulatory Potential of User Interfaces for AI Agent Governance

K. J. Kevin Feng, Tae Soo Kim, Rock Yuren Pang, Faria Huq, Tal August, Amy X. Zhang
2025-11-30
2512.00742v1

Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model

Junshu Tang, Jiacheng Liu, Jiaqi Li, Longhuang Wu, Haoyu Yang, Penghao Zhao, Siruis Gong, Xiang Yuan, Shuai Shao, Qinglin Lu
2025-11-28
2511.23429v1

Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering

Qiming Li, Xiaocheng Feng, Yixuan Ma, Zekai Ye, Ruihan Chen, Xiachong Feng, Bing Qin
2025-11-28
2511.23231v1

Are LLMs Good Safety Agents or a Propaganda Engine?

Neemesh Yadav, Francesco Ortu, Jiarui Liu, Joeun Yook, Bernhard Schölkopf, Rada Mihalcea, Alberto Cazzaniga, Zhijing Jin
2025-11-28
red teaming safety
2511.23174v1

Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks

Richard J. Young
2025-11-27
red teaming
2511.22047v1

Distillability of LLM Security Logic: Predicting Attack Success Rate of Outline Filling Attack via Ranking Regression

Tianyu Zhang, Zihang Xi, Jingyu Hua, Sheng Zhong
2025-11-27
red teaming
2511.22044v1

DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models

Mingue Park, Prin Phunyaphibarn, Phillip Y. Lee, Minhyuk Sung
2025-11-26
2511.21415v1

Self-Guided Defense: Adaptive Safety Alignment for Reasoning Models via Synthesized Guidelines

Yuhang Wang, Yanxu Zhu, Dongyuan Lu, Jitao Sang
2025-11-26
2511.21214v2

Self-Guided Defense: Adaptive Safety Alignment for Reasoning Models via Synthesized Guidelines

Yuhang Wang, Yanxu Zhu, Dongyuan Lu, Jitao Sang
2025-11-26
2511.21214v1

Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs

Dongkyu Derek Cho, Huan Song, Arijit Ghosh Chowdhury, Haotian An, Yawei Wang, Rohit Thekkanal, Negin Sokhandan, Sharlina Keshava, Hannah Marlowe
2025-11-26
safety
2511.21050v1

CameraMaster: Unified Camera Semantic-Parameter Control for Photography Retouching

Qirui Yang, Yang Yang, Ying Zeng, Xiaobin Hu, Bo Li, Huanjing Yue, Jingyu Yang, Peng-Tao Jiang
2025-11-26
2511.21024v1

BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents

Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley, Jerry Ma, Denis Yarats, Ninghui Li
2025-11-25
red teaming
2511.20597v1

Adversarial Confusion Attack: Disrupting Multimodal Large Language Models

Jakub Hoscilowicz, Artur Janicki
2025-11-25
red teaming
2511.20494v3

Adversarial Confusion Attack: Disrupting Multimodal Large Language Models

Jakub Hoscilowicz, Artur Janicki
2025-11-25
red teaming
2511.20494v2

Adversarial Confusion Attack: Disrupting Multimodal Large Language Models

Jakub Hoscilowicz, Artur Janicki
2025-11-25
red teaming
2511.20494v1