- 2024
- Meenatchi Sundaram Muthu Selva Annamalai
:
It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss. AISec@CCS 2024: 24-30 - Giovanni Apruzzese, Aurore Fass, Fabio Pierazzi:
When Adversarial Perturbations meet Concept Drift: An Exploratory Analysis on ML-NIDS. AISec@CCS 2024: 149-160 - Sayed Erfan Arefin, Abdul Serwadda:
Music to My Ears: Turning GPU Sounds into Intellectual Property Gold. AISec@CCS 2024: 196-207 - Christian Bungartz, Felix Boes, Michael Meier, Marc Ohm:
Towards Robust, Explainable, and Privacy-Friendly Sybil Detection. AISec@CCS 2024: 161-172 - Alberto Castagnaro, Mauro Conti, Luca Pajola:
Offensive AI: Enhancing Directory Brute-forcing Attack with the Use of Language Models. AISec@CCS 2024: 184-195 - Maor Biton Dor, Yisroel Mirsky:
Efficient Model Extraction via Boundary Sampling. AISec@CCS 2024: 1-11 - Nadav Gat, Mahmood Sharif:
Harmful Bias: A General Label-Leakage Attack on Federated Learning from Bias Gradients. AISec@CCS 2024: 31-41 - Jiankai Jin, Olga Ohrimenko, Benjamin I. P. Rubinstein:
Getting a-Round Guarantees: Floating-Point Attacks on Certified Robustness. AISec@CCS 2024: 53-64 - Shashwat Kumar, Francis Hahn, Stuart Millar, Xinming Ou:
Using LLM Embeddings with Similarity Search for Botnet TLS Certificate Detection. AISec@CCS 2024: 173-183 - Leo Hyun Park, Jaeuk Kim, Myung Gyo Oh, Jaewoo Park, Taekyoung Kwon:
Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training. AISec@CCS 2024: 101-112 - Dario Pasquini, Martin Strohmeier, Carmela Troncoso:
Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks. AISec@CCS 2024: 89-100 - Camila Roa, Maria Mahbub, Sudarshan Srinivasan, Edmon Begoli, Amir Sadovnik:
Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models. AISec@CCS 2024: 42-52 - Coen Schoof, Stefanos Koffas, Mauro Conti, Stjepan Picek:
EmoBack: Backdoor Attacks Against Speaker Identification Using Emotional Prosody. AISec@CCS 2024: 137-148 - Ryan Swope, Amol Khanna, Philip Doldo, Saptarshi Roy, Edward Raff:
Feature Selection from Differentially Private Correlations. AISec@CCS 2024: 12-23 - Behrad Tajalli, Stefanos Koffas, Gorka Abad, Stjepan Picek:
ELMs Under Siege: A Study on Backdoor Attacks on Extreme Learning Machines. AISec@CCS 2024: 125-136 - Zebin Yun, Achi-Or Weingarten, Eyal Ronen, Mahmood Sharif:
The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations. AISec@CCS 2024: 113-124 - Qi Zhao, Christian Wressnegger:
Adversarially Robust Anti-Backdoor Learning. AISec@CCS 2024: 77-88 - Yuxuan Zhu, Michael Mandulak, Kerui Wu, George M. Slota, Yuseok Jeon, Ka-Ho Chow, Lei Yu:
On the Robustness of Graph Reduction Against GNN Backdoor. AISec@CCS 2024: 65-76 - Maura Pintor, Xinyun Chen, Matthew Jagielski:
Proceedings of the 2024 Workshop on Artificial Intelligence and Security, AISec 2024, Salt Lake City, UT, USA, October 14-18, 2024. ACM 2024, ISBN 979-8-4007-1228-9 [contents] - 2023
- Tobias Lorenz, Marta Kwiatkowska, Mario Fritz:
Certifiers Make Neural Networks Vulnerable to Availability Attacks. AISec@CCS 2023: 67-78 - Sahar Abdelnabi, Kai Greshake, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz:
Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection. AISec@CCS 2023: 79-90 - Elizabeth Bates, Vasilios Mavroudis, Chris Hicks:
Reward Shaping for Happier Autonomous Cyber Security Agents. AISec@CCS 2023: 221-232 - Dudi Biton, Aditi Misra, Efrat Levy, Jaidip Kotak, Ron Bitton, Roei Schuster, Nicolas Papernot, Yuval Elovici, Ben Nassi:
The Adversarial Implications of Variable-Time Inference. AISec@CCS 2023: 103-114 - Tomás Chobola, Dmitrii Usynin, Georgios Kaissis:
Membership Inference Attacks Against Semantic Segmentation Models. AISec@CCS 2023: 43-53 - Theo Chow, Zeliang Kan, Lorenz Linhardt, Lorenzo Cavallaro, Daniel Arp, Fabio Pierazzi:
Drift Forensics of Malware Classifiers. AISec@CCS 2023: 197-207 - Benoît Coqueret, Mathieu Carbone, Olivier Sentieys, Gabriel Zaid:
When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence. AISec@CCS 2023: 127-138 - Mario D'Onghia, Federico Di Cesare, Luigi Gallo, Michele Carminati, Mario Polino, Stefano Zanero:
Lookin' Out My Backdoor! Investigating Backdooring Attacks Against DL-driven Malware Detectors. AISec@CCS 2023: 209-220 - Daniel Gibert, Giulio Zizzo, Quan Le:
Certified Robustness of Static Deep Learning-based Malware Detectors against Patch and Append Attacks. AISec@CCS 2023: 173-184 - Chris Hicks, Vasilios Mavroudis, Myles Foley, Thomas Davies, Kate Highnam, Tim Watson:
Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning. AISec@CCS 2023: 91-101 - Florian A. Hölzl, Daniel Rueckert, Georgios Kaissis:
Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models. AISec@CCS 2023: 11-22
