2,077+ academic papers on AI security, attacks, and defenses
Showing 2061–2077 of 2,077 papers
Panagiotis Michelakis, Yiannis Hadjiyiannis, Dimitrios Stamoulis
Evaluating AI agents that solve real-world tasks through function-call sequences remains an open challenge. Existing agentic benchmarks often reduce...
Hanbo Huang, Yiran Zhang, Hao Zheng +4 more
Large Language Models (LLMs) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming...
Anh Tu Ngo, Anupam Chattopadhyay, Subhamoy Maitra
In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as...
Wenkai Guo, Xuefeng Liu, Haolin Wang +3 more
Fine-tuning large language models (LLMs) with local data is a widely adopted approach for organizations seeking to adapt LLMs to their specific...
Adam Swanda, Amy Chang, Alexander Chen +3 more
The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across...
Maria Chiper, Radu Tudor Ionescu
Phishing attacks targeting both organizations and individuals are becoming an increasingly significant threat as technology advances. Current...
Dana A Abdullah, Dana Rasul Hamad, Bishar Rasheed Ibrahim +3 more
Altered fingerprint recognition (AFR) is challenging for biometric verification in applications such as border control, forensics, and fiscal...
Atousa Arzanipour, Rouzbeh Behnia, Reza Ebrahimi +1 more
Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with external...
Xiaofan Li, Xing Gao
In recent years, various software supply chain (SSC) attacks have posed significant risks to the global community. Severe consequences may arise if...
Wenhan Wu, Zheyuan Liu, Chongyang Gao +2 more
Current LLM unlearning methods face a critical security vulnerability that undermines their fundamental purpose: while they appear to successfully...
Tanmay Khule, Stefan Marksteiner, Jose Alguindigue +3 more
In modern automotive development, security testing is critical for safeguarding systems against increasingly advanced threats. Attack trees are...
Lauren Deason, Adam Bali, Ciprian Bejean +20 more
Today's cyber defenders are overwhelmed by a deluge of security alerts, threat intelligence signals, and shifting business context, creating an...
Md Jueal Mia, M. Hadi Amini
Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignment...
Xiyu Zeng, Siyuan Liang, Liming Lu +5 more
As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense...
Balazs Pejo, Marcell Frank, Krisztian Varga +2 more
This paper investigates the fragility of contribution evaluation in federated learning, a critical mechanism for ensuring fairness and incentivizing...
Tharcisse Ndayipfukamiye, Jianguo Ding, Doreen Sebastian Sarwatt +2 more
Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks (GANs) act as both...
Wence Ji, Jiancan Wu, Aiying Li +5 more
With the rapid advancement of large language models (LLMs), their robustness against adversarial manipulations, particularly jailbreak backdoor...
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