Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuning Bingquan Shen, Gaowen Liu, Sijia Liu, Yihua Zhang Published: 2025-03-14Area: Multimodal SafetyCitations: 7 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-03-14 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E7 / R3 (94%) | 7 |
| Safe Vision-Language Models via Unsafe Weights Manipulation Elia Peruzzo, Humphrey Shi, Massimiliano Mancini, Moreno D'Inc脿 Published: 2025-03-14Area: Multimodal SafetyCitations: 1 Tags: ai-safety, empirical, multimodal-safety | 2025-03-14 | Multimodal Safety | ai-safety, empirical, multimodal-safety | E5 / R3 (95%) | 1 |
| Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense Bryan Hooi, Chengcheng Tang, Jun Liu, Ming-Hsuan Yang Published: 2025-03-14Area: Multimodal SafetyCitations: 1 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-03-14 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E5 / R3 (95%) | 1 |
| Survey of Adversarial Robustness in Multimodal Large Language Models Chengze Jiang, Jie Gui, Minjing Dong, Zhuangzhuang Wang Published: 2025-03-18Area: Multimodal SafetyCitations: 11 Tags: adversarial-robustness, ai-safety, multimodal-safety, survey | 2025-03-18 | Multimodal Safety | adversarial-robustness, ai-safety, multimodal-safety, survey | E5 / R3 (95%) | 11 |
| MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks Bryan Hooi, Ming-Hsuan Yang, Wenhao You, Yiwei Wang Published: 2025-03-24Area: Multimodal SafetyCitations: 4 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-03-24 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E6 / R3 (96%) | 4 |
| Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots Erfan Shayegani, G M Shahariar, Lei Yu, Nael Abu-Ghazaleh Published: 2025-04-01Area: Multimodal SafetyCitations: - Tags: ai-safety, alignment-training, empirical, multimodal-safety | 2025-04-01 | Multimodal Safety | ai-safety, alignment-training, empirical, multimodal-safety | E5 / R3 (96%) | - |
| ShieldGemma 2: Robust and Tractable Image Content Moderation Aparna Joshi, Cai Xu, Dana Kurniawan, Dirichi Ike-Njoku Published: 2025-04-01Area: Multimodal SafetyCitations: 11 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-04-01 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E6 / R3 (96%) | 11 |
| AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization Chaohu Liu, Linli Xu, Tianyi Gui, Yu Liu Published: 2025-04-02Area: Multimodal SafetyCitations: 3 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-04-02 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E6 / R4 (94%) | 3 |
| PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization Aofan Liu, Ao Yang, Bin Wang, Lulu Tang Published: 2025-04-02Area: Multimodal SafetyCitations: 5 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-04-02 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E5 / R3 (96%) | 5 |
| Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks Jiawei Wang, Kin-Man Lam, Yicheng Fu, Yichun Feng Published: 2025-04-02Area: Multimodal SafetyCitations: - Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-04-02 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E6 / R3 (96%) | - |
| JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model Chaowei Xiao, Li Li, Shenzhe Zhu, Yi Nian Published: 2025-04-03Area: Multimodal SafetyCitations: - Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-04-03 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E5 / R4 (95%) | - |
| Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking Junhao Dong, Junxi Chen, Xiaohua Xie Published: 2025-04-08Area: Multimodal SafetyCitations: 5 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-04-08 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E5 / R3 (94%) | 5 |
| SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models An Zhang, Junfeng Fang, Kun Wang, Ruipeng Wang Published: 2025-04-09Area: Multimodal SafetyCitations: 34 Tags: adversarial-robustness, ai-safety, alignment-training, empirical, multimodal-safety | 2025-04-09 | Multimodal Safety | adversarial-robustness, ai-safety, alignment-training, empirical, multimodal-safety | E5 / R3 (96%) | 34 |
| Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models? Jian Liang, Jiyang Guan, Ran He, Yanbo Wang Published: 2025-04-14Area: Multimodal SafetyCitations: 7 Tags: ai-safety, alignment-training, empirical, multimodal-safety | 2025-04-14 | Multimodal Safety | ai-safety, alignment-training, empirical, multimodal-safety | E5 / R3 (93%) | 7 |
| VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization Jingjing Dong, Menglan Chen, Siheng Chen, WenHao Wang Published: 2025-04-17Area: Multimodal SafetyCitations: 6 Tags: ai-safety, alignment-training, empirical, multimodal-safety | 2025-04-17 | Multimodal Safety | ai-safety, alignment-training, empirical, multimodal-safety | E5 / R3 (96%) | 6 |
| Manipulating Multimodal Agents via Cross-Modal Prompt Injection Aishan Liu, Le Wang, Mingchuan Zhang, Shengshan Hu Published: 2025-04-19Area: Multimodal SafetyCitations: 21 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-04-19 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E5 / R3 (97%) | 21 |
| When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems Jiayang Liu, Jie Zhang, Luu Anh Tuan, Runyi Hu Published: 2025-04-29Area: Multimodal SafetyCitations: 3 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-04-29 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E5 / R3 (96%) | 3 |
| Transferable Adversarial Attacks on Black-Box Vision-Language Models Alexander Robey, Andy Zou, Chengming Xu, Haoqi Hu Published: 2025-05-02Area: Multimodal SafetyCitations: 7 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-05-02 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E6 / R3 (93%) | 7 |
| Adversarial Attacks in Multimodal Systems: A Practitioner's Survey Aman Raj, Ankit Shetgaonkar, Dipen Pradhan, Lakshit Arora Published: 2025-05-06Area: Multimodal SafetyCitations: 2 Tags: adversarial-robustness, ai-safety, multimodal-safety, survey | 2025-05-06 | Multimodal Safety | adversarial-robustness, ai-safety, multimodal-safety, survey | E6 / R3 (94%) | 2 |
| REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLMs Madhur Jindal, Saurabh Deshpande Published: 2025-05-07Area: Multimodal SafetyCitations: 3 Tags: ai-safety, benchmark, multimodal-safety, safety-evaluation | 2025-05-07 | Multimodal Safety | ai-safety, benchmark, multimodal-safety, safety-evaluation | E6 / R4 (99%) | 3 |
| X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP Hanxun Huang, James Bailey, Sarah Erfani, Xingjun Ma Published: 2025-05-08Area: Multimodal SafetyCitations: 14 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-05-08 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E5 / R4 (96%) | 14 |
| Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model Chi Chen, Jinan Xu, Kaiyu Huang, Xiangyu Shi Published: 2025-05-10Area: Multimodal SafetyCitations: 11 Tags: adversarial-robustness, ai-safety, alignment-training, empirical, multimodal-safety, safety-evaluation | 2025-05-10 | Multimodal Safety | adversarial-robustness, ai-safety, alignment-training, empirical, multimodal-safety, safety-evaluation | E5 / R3 (95%) | 11 |
| SafeVid: Toward Safety Aligned Video Large Multimodal Models Jiaxin Song, Xingjun Ma, Xin Wang, Yang Yao Published: 2025-05-17Area: Multimodal SafetyCitations: 4 Tags: ai-safety, alignment-training, empirical, multimodal-safety | 2025-05-17 | Multimodal Safety | ai-safety, alignment-training, empirical, multimodal-safety | E5 / R4 (95%) | 4 |
| Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs Huaibo Huang, Peipei Li, Ran He, Shuhan Xia Published: 2025-05-17Area: Multimodal SafetyCitations: 10 Tags: ai-safety, benchmark, multimodal-safety, safety-evaluation | 2025-05-17 | Multimodal Safety | ai-safety, benchmark, multimodal-safety, safety-evaluation | E4 / R3 (95%) | 10 |
| Backdoor Cleaning without External Guidance in MLLM Fine-tuning Bo Du, Jian Liang, Jinhe Bi, Mang Ye Published: 2025-05-22Area: Multimodal SafetyCitations: 14 Tags: ai-safety, empirical, multimodal-safety | 2025-05-22 | Multimodal Safety | ai-safety, empirical, multimodal-safety | E5 / R3 (96%) | 14 |
| Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models Dongsheng Shi, Gerard de Melo, Linlin Wang, Xiaoling Wang Published: 2025-05-22Area: Multimodal SafetyCitations: 1 Tags: ai-safety, alignment-training, empirical, multimodal-safety | 2025-05-22 | Multimodal Safety | ai-safety, alignment-training, empirical, multimodal-safety | E5 / R2 (95%) | 1 |
| Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models Cong Tian, Handing Wang, Yaochu Jin, Zhaoxin Wang Published: 2025-05-22Area: Multimodal SafetyCitations: 4 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-05-22 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E6 / R4 (97%) | 4 |
| Robustifying Vision-Language Models via Dynamic Token Reweighting Fenglong Ma, Jiacheng Liang, Jiawei Zhou, Rongyi Zhu Published: 2025-05-22Area: Multimodal SafetyCitations: 2 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-05-22 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E5 / R3 (96%) | 2 |
| JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models Jingyi Zheng, Mingchen Li, Shengmin Xu, Wenhan Dong Published: 2025-05-23Area: Multimodal SafetyCitations: 6 Tags: adversarial-robustness, ai-safety, benchmark, multimodal-safety | 2025-05-23 | Multimodal Safety | adversarial-robustness, ai-safety, benchmark, multimodal-safety | E5 / R3 (99%) | 6 |
| Attention! Your Vision Language Model Could Be Maliciously Manipulated Shaokang Wang, Shudong Zhang, Xiaosen Wang, Yuyang Luo Published: 2025-05-26Area: Multimodal SafetyCitations: 3 Tags: adversarial-robustness, ai-safety, empirical, multimodal-safety | 2025-05-26 | Multimodal Safety | adversarial-robustness, ai-safety, empirical, multimodal-safety | E7 / R3 (97%) | 3 |