7 papers
NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification
David D. Nguyen, The-Anh Ta, Yansong Gao +1
The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as ad…
Alert-ME: An Explainability-Driven Defense Against Adversarial Examples in Transformer-Based Text Classification
Bushra Sabir, Yansong Gao, Alsharif Abuadbba +1
Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial exampl…
Large Language Model Adversarial Landscape Through the Lens of Attack Objectives
Nan Wang, Kane Walter, Yansong Gao +1
Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an u…
Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World
Hua Ma, Alsharif Abuadbba, Yansong Gao +2
The exploration of backdoor vulnerabilities in object detectors, particularly in real-world scenarios, remains limited. A significant challenge lies in the absence of a natural phy…
From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting
Shigang Liu, Bushra Sabir, Seung Ick Jang +5
Large Language Models (LLMs) have shown remarkable potential in code generation, making them increasingly important in the field. However, the security issues of generated code hav…
Split Learning without Local Weight Sharing to Enhance Client-side Data Privacy
Ngoc Duy Pham, Tran Khoa Phan, Alsharif Abuadbba +3
Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. In SL training with multiple clients, the…