[AI Security] Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices, ESORICS 2022

Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Device

Younghan Lee, Sohee Jun, Yungi Cho, Woorim Han, Hyungon Moon, Yunheung Paek

European Symposium on Research in Computer Security (ESORICS)


0
0

International Papers

SW Security Practical Binary Code Similarity Detection with BERT-based Transferable Similarity Learning, ACSAC 2022
HW Security Accelerating N-bit Operations over TFHE on Commodity CPU-FPGA, ICCAD 2022
SW Security Exploring Effective Uses of the Tagged Memory for Reducing Bounds Checking Overheads (early access), The Journal of Supercomputing, July 2022
AI Security Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices, ESORICS 2022
AI Security A pilot study of machine-learning-based algorithms to assist integrated care for older community-dwelling adults, Computers, Informatics, Nursing (CIN), Feb 2022
AI Security A Data Embedding Scheme for Efficient Program Behavior Modeling with Neural Networks (early access), IEEE Transactions on Emerging Topics in Computational Intelligence (Impact Factor: 8.28), May 2022
HW Security A Hardware Platform for Ensuring OS Kernel Integrity on RISC-V, MDPI Electronics, August 2021
AI Security Panop: Mimicry-Resistant ANN-based Distributed NIDS for IoT Networks, IEEE Access, July 2021
AI Security Learn2Evade: Learning-based Generative Model for Evading PDF Malware Classifiers, IEEE Transactions on Artificial Intelligence, July 2021
HW Security Ambassy: A Runtime Framework to Delegate Trusted Applications in an ARM/FPGA Hybrid System (early access), IEEE Transactions on Mobile Computing (TMC), Jun 2021
HW Security MeetGo: A Trusted Execution Environment for Remote Applications on FPGA (early access), IEEE Access, Mar 2021
SW Security ExpRace: Exploiting Kernel Races through Raising Interrupts (conditional accept), USENIX Security Symposium (Security), August 2021
SW Security Constraint-guided Directed Greybox Fuzzing (conditional accept), USENIX Security Symposium (Security), August 2021
SW Security M2MON: Building an MMIO-based Security Reference Monitor for Unmanned Vehicles (to appear), USENIX Security Symposium (Security), August 2021
SW Security KARD: Lightweight Data Race Detection with Per-Thread Memory Protection (to appear), International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), April 2021
SW Security BlackMirror: Preventing Wallhacks in 3D Online FPS Games, ACM Conference on Computer and Communications Security (CCS), Nov 2020
SW Security CrFuzz: Fuzzing Multi-purpose Programs through Input Validation, ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE), Nov 2020
SW Security Vessels: Efficient and Scalable Deep Learning Prediction on Trusted Processors, ACM Symposium on Cloud Computing (SoCC), Oct 2020
SW Security Exploiting Kernel Races through Taming Thread Interleaving, BlackHat USA, Sep 2020
SW Security A Tale of Two Trees: One Writes, and Other Reads. Optimized Oblivious Accesses to Large-Scale Blockchains, Privacy Enhancing Technologies Symposium (PETS), July 2020