Ndss 2026

112 papers

Top Research Directions

Research directions most represented by Ndss 2026 papers.

Neutralizing Neural Backdoors Through Targeted Neuron Pruning 1
Latent Feature Decoupling for Backdoor Defense 1
Instance Adaptive Prompting for Vision Language Models 1
Sybil Attacks in Open Distributed Systems 1
Backdoor Defense Under Clean Data Scarcity 1
Physical Side Channel Leakage and Hardware Countermeasures 1
Side Channel Vulnerabilities in Trusted Execution Environments 1
Clean Accuracy Degradation in Machine Learning Defenses 1

Top Authors

AuthorPapers
Jun Dai2
Xue Tan2
Chaoyu Zhang1
Chong Wang1
Jie Zhang1
Kangjie Chen1
Mingyu Luo1
Shengli Zhang1
Shiqian Zhao1
Siew Kei Lam1
Tianwei Zhang1
Wenjie Qu1
Yihao Huang1
Yiming Li1
Ying Li1
Yi Xie1

Papers

Title
Towards Effective Prompt Stealing Attack against\\Text-to-Image Diffusion Models
TranSPArent: Taint-style Vulnerability Detection in Generic Single Page Applications through Automated Framework Abstraction
Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias
Understanding the Stealthy BGP Hijacking Risk in the ROV Era
Unshaken by Weak Embedding: Robust Probabilistic Watermarking for Dataset Copyright Protection
User-Space Dependency-Aware Rehosting for Linux-Based Firmware Binaries
Validity Is Not Enough: Uncovering the Security Pitfall in Chainlink's Off-Chain Reporting Protocol
VDORAM: Towards a Random Access Machine with Both Public Verifiability and Distributed Obliviousness
VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
ViGText: Deepfake Image Detection with Vision-Language Model Explanations and Graph Neural Networks
Was My Data Used for Training? Membership Inference in Open-Source LLMs via Neural Activations
ZKSL: Verifiable and Efficient Split Federated Learning via Asynchronous Zero-Knowledge Proofs

« prev Page 3/3