2,077+ academic papers on AI security, attacks, and defenses
Showing 321–340 of 715 papers
Clear filtersBinh Nguyen, Thai Le
Audio Language Models (ALMs) offer a promising shift towards explainable audio deepfake detections (ADDs), moving beyond \textit{black-box}...
Xiao Lin, Philip Li, Zhichen Zeng +6 more
Despite rich safety alignment strategies, large language models (LLMs) remain highly susceptible to jailbreak attacks, which compromise safety...
Zejian Chen, Chaozhuo Li, Chao Li +3 more
This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs),...
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
As Large Language Models (LLMs) are increasingly deployed in safety-critical domains, rigorously evaluating their robustness against adversarial...
Xiangdong Hu, Yangyang Jiang, Qin Hu +1 more
Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous...
Xiangzhe Yuan, Zhenhao Zhang, Haoming Tang +1 more
As LLMs gain persuasive agentic capabilities through extended dialogues, they introduce novel risks in multi-turn conversational scams that...
Xi Wang, Songlei Jian, Shasha Li +5 more
Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a...
Yuetian Chen, Yuntao Du, Kaiyuan Zhang +4 more
Most membership inference attacks (MIAs) against Large Language Models (LLMs) rely on global signals, like average loss, to identify training data....
Dinghong Song, Zhiwei Xu, Hai Wan +3 more
Model quantization is critical for deploying large language models (LLMs) on resource-constrained hardware, yet recent work has revealed severe...
Scott Thornton
Large language models remain vulnerable to jailbreak attacks, and single-layer defenses often trade security for usability. We present TRYLOCK, the...
Devang Kulshreshtha, Hang Su, Chinmay Hegde +1 more
Most jailbreak methods achieve high attack success rates (ASR) but require attacker LLMs to craft adversarial queries and/or demand high query...
Alexandre Le Mercier, Chris Develder, Thomas Demeester
State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language models, with linear time complexity. Yet, their...
Alexandre Le Mercier, Chris Develder, Thomas Demeester
State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language models, with linear time complexity. Yet, their...
Yun Bian, Yi Chen, HaiQuan Wang +2 more
Software vulnerability detection can be formulated as a binary classification problem that determines whether a given code snippet contains security...
Xin Wang, Yunhao Chen, Juncheng Li +7 more
The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety...
Songyang Liu, Chaozhuo Li, Rui Pu +5 more
Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely...
M P V S Gopinadh, S Mahaboob Hussain
Large Language Models (LLMs) are integral to modern AI applications, but their safety alignment mechanisms can be bypassed through adversarial prompt...
Yueyan Dong, Minghui Xu, Qin Hu +5 more
Low-Rank Adaptation (LoRA) has become a popular solution for fine-tuning large language models (LLMs) in federated settings, dramatically reducing...
Md Mahbub Hasan, Marcus Sternhagen, Krishna Chandra Roy
Additive manufacturing (AM) is rapidly integrating into critical sectors such as aerospace, automotive, and healthcare. However, this cyber-physical...
Md Hasan Saju, Maher Muhtadi, Akramul Azim
The rapid advancement of Large Language Models (LLMs) presents new opportunities for automated software vulnerability detection, a crucial task in...
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert