2,560+ academic papers on AI security, attacks, and defenses
Showing 721–740 of 982 papers
Clear filtersLucas Fenaux, Christopher Srinivasa, Florian Kerschbaum
Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of...
Lama Sleem, Jerome Francois, Lujun Li +3 more
Jailbreak attacks designed to bypass safety mechanisms pose a serious threat by prompting LLMs to generate harmful or inappropriate content, despite...
Farhad Abtahi, Fernando Seoane, Iván Pau +1 more
Healthcare AI systems face major vulnerabilities to data poisoning that current defenses and regulations cannot adequately address. We analyzed eight...
Runpeng Geng, Yanting Wang, Chenlong Yin +3 more
Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an...
Srikant Panda, Avinash Rai
Large Language Models (LLMs) are commonly evaluated for robustness against paraphrased or semantically equivalent jailbreak prompts, yet little...
Shuaitong Liu, Renjue Li, Lijia Yu +3 more
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have...
Yudong Yang, Xuezhen Zhang, Zhifeng Han +6 more
Recent progress in LLMs has enabled understanding of audio signals, but has also exposed new safety risks arising from complex audio inputs that are...
Zihan Wang, Guansong Pang, Wenjun Miao +2 more
Recent advances in Large Visual Language Models (LVLMs) have demonstrated impressive performance across various vision-language tasks by leveraging...
Xin Zhao, Xiaojun Chen, Bingshan Liu +3 more
Generative vision-language models like Stable Diffusion demonstrate remarkable capabilities in creative media synthesis, but they also pose...
Shigeki Kusaka, Keita Saito, Mikoto Kudo +3 more
Large language models (LLMs) are increasingly deployed in real-world systems, making it critical to understand their vulnerabilities. While data...
Hongyi Li, Chengxuan Zhou, Chu Wang +5 more
Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models...
Zixun Xiong, Gaoyi Wu, Qingyang Yu +5 more
Given the high cost of large language model (LLM) training from scratch, safeguarding LLM intellectual property (IP) has become increasingly crucial....
Tiago Machado, Maysa Malfiza Garcia de Macedo, Rogerio Abreu de Paula +5 more
This work aims to investigate how different Large Language Models (LLMs) alignment methods affect the models' responses to prompt attacks. We...
Giorgio Piras, Raffaele Mura, Fabio Brau +3 more
Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing...
Yuxuan Zhou, Yuzhao Peng, Yang Bai +7 more
Large Vision-Language Models (VLMs) are susceptible to jailbreak attacks: researchers have developed a variety of attack strategies that can...
Ke Jia, Yuheng Ma, Yang Li +1 more
We revisit the problem of generating synthetic data under differential privacy. To address the core limitations of marginal-based methods, we propose...
Yaxin Xiao, Qingqing Ye, Zi Liang +4 more
Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries...
Xingyu Li, Xiaolei Liu, Cheng Liu +4 more
As large language models (LLMs) scale, their inference incurs substantial computational resources, exposing them to energy-latency attacks, where...
Hanlin Cai, Houtianfu Wang, Haofan Dong +3 more
Internet of Agents (IoA) envisions a unified, agent-centric paradigm where heterogeneous large language model (LLM) agents can interconnect and...
Zhisheng Zhang, Derui Wang, Yifan Mi +6 more
Recent advancements in speech synthesis technology have enriched our daily lives, with high-quality and human-like audio widely adopted across...
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