Location: Room 121A, Pennsylvania Convention Center, Philadelphia
Keynotes
Nathaniel D. Bastian
Chief Scientist and Director
Office of Science & Technology - Army Cyber Institute at West Point
Talk Title: Operational AI Red Teaming: Gaps and Opportunities
Edward Raff
Director of Emerging AI, Booz Allen Hamilton
Talk Title: Why I hate Parsers and You Should Too
| Authors |
Paper (Accepted) |
| Matthew J. Turner, Mike Carenzo, Jackie Lasky, James Morris-King, James Ross |
Technique Inference Engine: A Recommender Model to Support Cyber Threat Hunting |
| Erick Galinkin, Emmanouil Pountourakis, Spiros Mancoridis |
Towards Attacker Type Agnostic Cyber Defense Agents |
| Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun Chandrasekaran |
LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles |
| Zain ul Abdeen, Ahmad Tawaha, Padmaksha Roy, Ruoxi Jia, Laura Freeman, Peter Beling, Chen-Ching Liu, Alberto Sangiovanni-Vincentelli, Ming Jin |
Defense against Joint Poisoning and Evasion Attacks: A Case Study of DERMS |
| Tommy Nguyen, Mehmet Ergezer, Christian Green |
AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models |
| Christian Green, Mehmet Ergezer, Abdurrahman Zeybey |
Targeted View-Invariant Adversarial Perturbations for 3D Object Recognition |
| Elvin Li, Zhengli Shang, Onat Gungor, Tajana Rosing |
SAFE: Self-Supervised Anomaly Detection Framework for Intrusion Detection |
| Yue Sun, Rick S. Blum, Parv Venkitasubramaniam |
Unifying Explainable Anomaly Detection and Root Cause Analysis in Dynamical Systems |
| Amir Jevnisek, Vlad Rakhlin, Shai Avidan |
Coordinate Descent for Network Linearization |
| Ilan Schvartzman, Roei Sarussi, Maor Ashkenazi, Ido kringel, Yaniv Tocker, Tal Furman Shohet |
A New Dataset and Methodology for Malicious URL Classification |
| Tianhao Li, Jingyu Lu , Chuangxin Chu , Tianyu Zeng , Yujia Zheng, Mei Li, Haotian Huang, Bin Wu, Zuoxian Liu, Kai Ma, Xuejing Yuan, Xingkai Wang, Keyan Ding, Huajun Chen, Qiang Zhang |
SCISAFEEVAL: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks |
| Erick Galinkin, Martin Sablotny |
Improved Large Language Model Jailbreak Detection via Pretrained Embeddings |
| Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang |
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment |
| Gary A. McCully, John Hastings, Shengjie Xu, Adam Fortier |
Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code |
| Fernando Martinez, Lesther Santana, Mohamed Rahouti |
Learning in Multiple Spaces: Few-Shot Network Attack Detection with Metric-Fused Prototypical Networks |
| Domenic Rosati, Giles Edkins, Harsh Raj, David Atanasov, Subhabrata Majumdar, Janarthanan Rajendran, Frank Rudzicz, Hassan Sajjad |
Mitigating Unsafe Feedback with Learning Constraints |
| Jared Claypoole, Steven Cheung, Ashish Gehani, Vinod Yegneswaran, Ahmad Ridley |
Interpreting Agent Behaviors in Reinforcement-Learning-Based Cyber-Battle Simulation Platforms |
| Ahtesham Bakht, Dinesh Sharma, Ankit Shah, Nathaniel D. Bastian |
A Reinforcement Learning and Optimization Framework for Crafting Stealthy Poisons through Image Embedding Manipulation |
| Chun Kai Ling, Jakub Cerny, Chin Hui Han, Christian Kroer, Garud Iyengar |
How Deep Is Your Defense-in-Depth? Hardening Cybersecurity Network Control Against Adaptive Attackers |
| Minami Someya, Akira Otsuka |
RevLlama: Recovering Function Names via Rationale Distillation from Large to Small Language Models |
