CCS 2021
118 papers
The 2021 edition of the ACM Conference on Computer and Communications Security (CCS) featured 163 papers, with a strong emphasis on the intersection of machine learning and privacy. Key research directions included privacy-preserving inference for large models, sparsity-aware machine learning, and the security of intermediate representations in split learning. Adversarial machine learning was also a major theme, featuring work on frequency domain defenses against perturbations and poisoning attacks on anomaly detection baselines.
In network security, researchers explored real-time intrusion detection, DDoS deterrence via multi-hop traffic divergence, and adversarial traffic shaping for metadata privacy. Notable studies addressed practical threats such as deep learning-based speech synthesis attacks and leakage-abuse attacks on searchable encryption. System security research focused on hardware-supported fuzzing and the development of ontology-driven knowledge graphs for Android malware. Prolific contributors to this year's program included Shouling Ji, Minhui Xue, and Qi Li. The proceedings reflected a balanced focus on enhancing cryptographic primitives, such as homomorphic encryption, and addressing emerging vulnerabilities in distributed and federated environments.
Top Research Directions
Research directions most represented by CCS 2021 papers.
Top Authors
Impactful Papers
Papers from CCS 2021 that shaped research clusters.
Foundational
Backdoor Pre-trained Models Can Transfer to All
foundational
Attention Hijacking in Backdoored Transf
Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Class
foundational
Behavioral and Vulnerability Transfer in
Influential
An Ontology-driven Knowledge Graph for Android Malware
influential
Automated Triage of Cybersecurity Alerts
Unleashing the Tiger: Inference Attacks on Split Learning
influential
Privacy Leakage from Intermediate Featur
A Formally Verified Configuration for Hardware Security Modules in the Cloud
influential
Oracle Guided SAT Attacks on Logic Locki
Unleashing the Tiger: Inference Attacks on Split Learning
influential
Reconstructing Private Data from Model G
Papers
« prev Page 3/3