2,077+ academic papers on AI security, attacks, and defenses
Showing 381–400 of 809 papers
Clear filtersFumiya Morimoto, Ryuto Morita, Satoshi Ono
Deep neural network-based classifiers are prone to errors when processing adversarial examples (AEs). AEs are minimally perturbed input data...
Haoran Gu, Handing Wang, Yi Mei +2 more
The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While...
Xiaoze Liu, Weichen Yu, Matt Fredrikson +2 more
The open-weight language model ecosystem is increasingly defined by model composition techniques (such as weight merging, speculative decoding, and...
Manish Bhatt, Adrian Wood, Idan Habler +1 more
Production LLM agents with tool-using capabilities require security testing despite their safety training. We adapt Go-Explore to evaluate...
Ruben Neyroud, Sam Corley
While most LLMs are autoregressive, diffusion-based LLMs have recently emerged as an alternative method for generation. Greedy Coordinate Gradient...
Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1 more
Semantic communications conveys task-relevant meaning rather than focusing solely on message reconstruction, improving bandwidth efficiency and...
Pankayaraj Pathmanathan, Michael-Andrei Panaitescu-Liess, Cho-Yu Jason Chiang +1 more
Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm to enhance large language models (LLMs) with external knowledge, reducing...
Yuan Xin, Dingfan Chen, Linyi Yang +2 more
As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model...
Ruixuan Huang, Qingyue Wang, Hantao Huang +4 more
Mixture-of-Experts architectures have become the standard for scaling large language models due to their superior parameter efficiency. To...
Roee Ziv, Raz Lapid, Moshe Sipper
Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security...
Jiawei Liu, Zhuo Chen, Rui Zhu +4 more
Neural ranking models have achieved remarkable progress and are now widely deployed in real-world applications such as Retrieval-Augmented Generation...
Zhen Liang, Hai Huang, Zhengkui Chen
Large language models (LLMs), such as ChatGPT, have achieved remarkable success across a wide range of fields. However, their trustworthiness remains...
Soham Padia, Dhananjay Vaidya, Ramchandra Mangrulkar
Securing blockchain-enabled IoT networks against sophisticated adversarial attacks remains a critical challenge. This paper presents a trust-based...
Zongmin Zhang, Zhen Sun, Yifan Liao +5 more
Prompt-driven Video Segmentation Foundation Models (VSFMs) such as SAM2 are increasingly deployed in applications like autonomous driving and digital...
Jiayu Hu, Beibei Li, Jiangwei Xia +3 more
While Vision-Language Models (VLMs) have garnered increasing attention in the AI community due to their promising practical applications, they...
Mengqi He, Xinyu Tian, Xin Shen +4 more
Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, a measure of model uncertainty,...
Tsogt-Ochir Enkhbayar
Warning-framed content in training data (e.g., "DO NOT USE - this code is vulnerable") does not, it turns out, teach language models to avoid the...
Tian Li, Bo Lin, Shangwen Wang +1 more
Retrieval-Augmented Code Generation (RACG) is increasingly adopted to enhance Large Language Models for software development, yet its security...
Duo Chai, Zizhen Liu, Shuhuai Wang +4 more
Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time,...
Tianwei Lan, Farid Naït-Abdesselam
The rapid growth in both the scale and complexity of Android malware has driven the widespread adoption of machine learning (ML) techniques for...
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