English
Related papers

Related papers: AMIA: Automatic Masking and Joint Intention Analys…

200 papers

Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility to privacy leakage via Membership Inference Attacks (MIA) remains…

Machine Learning · Computer Science 2026-02-10 Yuetian Chen , Kaiyuan Zhang , Yuntao Du , Edoardo Stoppa , Charles Fleming , Ashish Kundu , Bruno Ribeiro , Ninghui Li

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Computation and Language · Computer Science 2025-11-04 Peng Ding , Jun Kuang , Wen Sun , Zongyu Wang , Xuezhi Cao , Xunliang Cai , Jiajun Chen , Shujian Huang

The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic…

Cryptography and Security · Computer Science 2026-05-19 Yanyun Wang , Yu Huang , Zi Liang , Xixin Wu , Li Liu

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Machine Learning · Computer Science 2025-07-08 Xin Wei Chia , Swee Liang Wong , Jonathan Pan

Membership Inference Attack (MIA) aims to determine whether a specific data sample was included in the training dataset of a target model. Traditional MIA approaches rely on shadow models to mimic target model behavior, but their…

Information Retrieval · Computer Science 2026-03-20 Li Cuihong , Huang Xiaowen , Yin Chuanhuan , Sang Jitao

Membership Inference Attacks (MIAs) aim to determine whether a specific data point was included in the training set of a target model. Although there are have been numerous methods developed for detecting data contamination in large…

Machine Learning · Computer Science 2025-12-03 Anton Emelyanov , Sergei Kudriashov , Alena Fenogenova

Deep Learning (DL) techniques allow ones to train models from a dataset to solve tasks. DL has attracted much interest given its fancy performance and potential market value, while security issues are amongst the most colossal concerns.…

Cryptography and Security · Computer Science 2020-05-19 Hongwei Huang , Weiqi Luo , Guoqiang Zeng , Jian Weng , Yue Zhang , Anjia Yang

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…

Cryptography and Security · Computer Science 2026-01-06 Jirui Yang , Zheyu Lin , Zhihui Lu , Yinggui Wang , Lei Wang , Tao Wei , Qiang Duan , Xin Du , Shuhan Yang

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

Cryptography and Security · Computer Science 2025-06-13 Kaiyuan Zhang , Siyuan Cheng , Hanxi Guo , Yuetian Chen , Zian Su , Shengwei An , Yuntao Du , Charles Fleming , Ashish Kundu , Xiangyu Zhang , Ninghui Li

Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 In Chong Choi , Jiacheng Zhang , Feng Liu , Yiliao Song

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training…

Cryptography and Security · Computer Science 2026-01-08 Zejian Chen , Chaozhuo Li , Chao Li , Xi Zhang , Litian Zhang , Yiming He

As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real-world tasks. However, MLLMs face significant security…

Cryptography and Security · Computer Science 2024-10-23 Fenghua Weng , Yue Xu , Chengyan Fu , Wenjie Wang

Membership inference attacks (MIAs) aim to determine whether a specific example was used to train a given language model. While prior work has explored prompt-based attacks such as ReCALL, these methods rely heavily on the assumption that…

Computation and Language · Computer Science 2026-01-27 Gyuwan Kim , Yang Li , Evangelia Spiliopoulou , Jie Ma , William Yang Wang

Membership inference attack (MIA) has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's…

Cryptography and Security · Computer Science 2025-06-04 Jing Xue , Zhishen Sun , Haishan Ye , Luo Luo , Xiangyu Chang , Ivor Tsang , Guang Dai

There is growing interest in ensuring that large language models (LLMs) align with human values. However, the alignment of such models is vulnerable to adversarial jailbreaks, which coax LLMs into overriding their safety guardrails. The…

Machine Learning · Computer Science 2024-07-22 Patrick Chao , Alexander Robey , Edgar Dobriban , Hamed Hassani , George J. Pappas , Eric Wong

Defending LLMs against adversarial jailbreak attacks remains an open challenge. Existing defenses rely on binary classifiers that fail when adversarial input falls outside the learned decision boundary, and repeated fine-tuning is…

Cryptography and Security · Computer Science 2026-02-24 Chun Yan Ryan Kan , Tommy Tran , Vedant Yadav , Ava Cai , Kevin Zhu , Ruizhe Li , Maheep Chaudhary

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Jingru Li , Wei Ren , Tianqing Zhu

We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking…

Cryptography and Security · Computer Science 2025-09-10 Qiming Guo , Jinwen Tang , Xingran Huang

Membership inference attacks (MIAs) reveal whether specific data was used to train machine learning models, serving as important tools for privacy auditing and compliance assessment. Recent studies have reported that MIAs perform only…

Machine Learning · Computer Science 2025-09-09 Disha Makhija , Manoj Ghuhan Arivazhagan , Vinayshekhar Bannihatti Kumar , Rashmi Gangadharaiah

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…

Cryptography and Security · Computer Science 2025-07-15 William Hackett , Lewis Birch , Stefan Trawicki , Neeraj Suri , Peter Garraghan