2,529+ academic papers on AI security, attacks, and defenses
Showing 801–820 of 867 papers
Clear filtersSanthosh KumarRavindran
The rapid adoption of large language models (LLMs) in enterprise systems exposes vulnerabilities to prompt injection attacks, strategic deception,...
Buyun Liang, Liangzu Peng, Jinqi Luo +3 more
Large Language Models (LLMs) are increasingly deployed in high-risk domains. However, state-of-the-art LLMs often exhibit hallucinations, raising...
Yu Cui, Sicheng Pan, Yifei Liu +2 more
Large language models (LLMs) have been widely deployed in Conversational AIs (CAIs), while exposing privacy and security threats. Recent research...
Yanjie Li, Yiming Cao, Dong Wang +1 more
Multimodal agents built on large vision-language models (LVLMs) are increasingly deployed in open-world settings but remain highly vulnerable to...
Xiangxiang Chen, Peixin Zhang, Jun Sun +2 more
Model quantization is a popular technique for deploying deep learning models on resource-constrained environments. However, it may also introduce...
Yulin Chen, Haoran Li, Yuan Sui +2 more
With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However,...
Rabeya Amin Jhuma, Mostafa Mohaimen Akand Faisal
This study explored how in-context learning (ICL) in large language models can be disrupted by data poisoning attacks in the setting of public health...
Maraz Mia, Mir Mehedi A. Pritom
Explainable Artificial Intelligence (XAI) has aided machine learning (ML) researchers with the power of scrutinizing the decisions of the black-box...
Javad Rafiei Asl, Sidhant Narula, Mohammad Ghasemigol +2 more
Large Language Models (LLMs) have revolutionized natural language processing but remain vulnerable to jailbreak attacks, especially multi-turn...
Sanket Badhe
We present LegalSim, a modular multi-agent simulation of adversarial legal proceedings that explores how AI systems can exploit procedural weaknesses...
Xinzhe Huang, Wenjing Hu, Tianhang Zheng +5 more
Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with...
Yu He, Yifei Chen, Yiming Li +5 more
In recent years, RAG has emerged as a key paradigm for enhancing large language models (LLMs). By integrating externally retrieved information, RAG...
Zhixin Xie, Xurui Song, Jun Luo
Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak...
Chinthana Wimalasuriya, Spyros Tragoudas
Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect...
Zhaorun Chen, Xun Liu, Mintong Kang +4 more
As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation...
Chengquan Guo, Chulin Xie, Yu Yang +6 more
Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic...
Jonathan Sneh, Ruomei Yan, Jialin Yu +6 more
As LLMs increasingly power agents that interact with external tools, tool use has become an essential mechanism for extending their capabilities....
Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar +3 more
Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction...
Kedong Xiu, Churui Zeng, Tianhang Zheng +6 more
Existing gradient-based jailbreak attacks typically optimize an adversarial suffix to induce a fixed affirmative response, e.g., ``Sure, here...
Milad Nasr, Yanick Fratantonio, Luca Invernizzi +7 more
As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level...
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