Please upload your slides or a introduction (Chinese or English) of your presentation in advance, such as conference, title, abstract，which can be written in the form of markdown. Please add your title in the agenda.
Location： Zetonglou 104
Time: Friday 18:00-20:00 Welcome to attend the seminar!
| Date | Speaker | Title | |
|---|---|---|---|
| 1 | 2020.12.25 | 陈安莹 施程辉 |
CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching, NIPS 2020 Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks, NIPS 2018 |
| 2 | 2021.1.1 | 陈源 邱鹏宇 |
sFuzz: An Efficient Adaptive Fuzzer for Solidity Smart Contracts, ICSE 2020 Practical Traffic Analysis Attacks on Secure Messaging Applications, NDSS 2020 |
| 3 | 2021.1.8 | 王琴应 应燕芸 |
APEX: A Verified Architecture for Proofs of Execution on Remote Devices under Full Software Compromise, USENIX Security 2020 |
| 4 | 2021.1.15 | 唐嘉蔚 刘丁豪 |
The Impact of Ad-Blockers on Product Search and Purchase Behavior: A Lab Experiment, USENIX Security 2020 MVP: Detecting Vulnerabilities using Patch-Enhanced Vulnerability Signatures, USENIX Security 2020 |
| 5 | 2021.1.22 | 张耀 付冲 |
Adversarial Preprocessing: Understanding and Preventing Image-Scaling Attacks in Machine Learning, USENIX Security 2020 A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models, ACM CCS 2020 |
| 6 | 2021.1.29 | 马哲 向意 |
Exploring Simple Siamese Representation Learning, Arxiv 2020 Fuzzing File Systems via Two-Dimensional Input Space Exploration, IEEE S&P 2019 |
| 7 | 2021.2.5 | ||
| 8 | 2021.2.12 | ||
| 9 | 2021.2.19 | 付之笑 陈越尧 |
Multi-modal Transformer for Video Retrieval, ECCV 2020 AURORA: Statistical Crash Analysis for Automated Root Cause Explanation, USENIX Security 2020 |
| 10 | 2021.2.26 | ||
| 11 | 2021.3.5 | 沈鹿嘉 甘雨由 |
Data Poisoning Attacks to Deep Learning Based Recommender Systems, NDSS 2021 Implicit Semantic Data Augmentation for Deep Networks, NeurIPS 2019 |
| 12 | 2021.3.12 | 卢令令 谢之源 |
Betrayal, Distrust, and Rationality: Smart Counter-Collusion Contracts for Verifiable Cloud Computing, ACM CCS 2017 Into the Deep Web: Understanding E-commerce Fraud from Autonomous Chat with Cybercriminals, NDSS 2021 |
| 13 | 2021.3.19 | 邱鹏宇 刘丁豪 |
Model Watermarking for Image Processing Networks, AAAI 2020 Finding Bugs Using Your Own Code: Detecting Functionally-similar yet Inconsistent Code, USENIX Security 2021 |
| 14 | 2021.3.26 | 马哲 沈鹿嘉 |
Is Space-Time Attention All You Need for Video Understanding?, arXiv 2021 Manipulating the Byzantine: Optimizing Model Poisoning Attacks and Defenses for Federated Learning, NDSS 2021 |
| 15 | 2021.4.2 | 刘沛宇 梁红 |
Understanding Worldwide Private Information Collection on Android, NDSS 2021 PANGOLIN: Incremental Hybrid Fuzzing with Polyhedral Path Abstraction, IEEE S&P 2020 |
| 16 | 2021.4.9 | 张耀 王琴应 |
CloudLeak: Large-Scale Deep Learning Models Stealing Through Adversarial Examples, NDSS 2021 Data Privacy in Trigger-Action IoT Systems, IEEE S&P 2021 |
| 17 | 2021.4.16 | 陈源 梁红 |
EVMPatch: Timely and Automated Patching of Ethereum Smart Contracts, USENIX Security 2021 Neuro-Symbolic Execution: Augmenting Symbolic Execution with Neural Constraints, NDSS 2019 |
| 18 | 2021.4.23 | 应燕芸 付之笑 |
Deep learning for in vivo near-infrared imaging, PNAS 2021 Multimodal Analytics for Real-world News using Measures of Cross-modal Entity Consistency, ICMR 2020 |
| 19 | 2021.4.30 | 卢令令 甘雨由 |
Blockene: A High-throughput Blockchain Over Mobile Devices, OSDI 2020 Towards Efficient Visual Explanation of Black-Box Neural Network, PREVIEW |
| 20 | 2021.5.7 | 陈越尧 唐嘉蔚 |
Detecting Kernel Memory Leaks in Specialized Modules with Ownership Reasoning, NDSS 2021 Evade Deep Image Retrieval by Stashing Private Images in the Hash Space, CVPR 2020 |
| 21 | 2021.5.14 | 施程辉 付冲 |
Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment, ACM CCS 2019 Composite Backdoor Attack for Deep Neural Network by Mixing Existing Benign Features, ACM CCS 2020 |
| 22 | 2021.5.21 | 马哲 向意 |
Video Corpus Moment Retrieval with Contrastive Learning, SIGIR 2021 SAVIOR: Towards Bug-Driven Hybrid Testing, IEEE S&P 2020 |
| 23 | 2021.5.28 | 邱鹏宇 刘丁豪 |
DeepDyve: Dynamic Verification for Deep Neural Networks, ACM CCS 2020 On the Feasibility of Stealthily Introducing Vulnerabilities in Open-Source Software via Hypocrite Commits |
| 24 | 2021.6.4 | 段宇萱 叶童 |
PDiff: Semantic-based Patch Presence Testing for Downstream Kernels, ACM CCS 2020 |
| 25 | 2021.6.11 | 刘丁豪 沈鹿嘉 |
Understanding and Detecting Disordered Error Handling with Precise Function Pairing, USENIX Security 2021 Poisoning the Unlabeled Dataset of Semi-Supervised Learning, arXiv 2021 |
| 26 | 2021.6.18 | 付冲 侯黎阳 |
You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion, USENIX Security 2021 SQUIRREL: Testing Database Management Systems with Language Validity and Coverage Feedback, ACM CCS 2020 |
| 27 | 2021.6.25 | 虞楚尔 段宇萱 |
PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking, USENIX Security 2021 WaveGuard: Understanding and Mitigating Audio Adversarial Examples, USENIX Security 2021 |
| 28 | 2021.7.2 | 梁红 向意 |
SLIME: Program-sensitive Energy Allocation for Fuzzing HFL: Hybrid Fuzzing on the Linux Kernel, NDSS 2020 |
| 29 | 2021.7.9 | 马哲 陈越尧 |
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training, arXiv 2021 Not All Coverage Measurements Are Equal: Fuzzing by Coverage Accounting for Input Prioritization, NDSS 2020 |
| 30 | 2021.7.16 | 陈源 张耀 |
WINNIE : Fuzzing Windows Applications with Harness Synthesis and Fast Cloning, NDSS 2021 Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding, IEEE S&P 2021 |
| 31 | 2021.7.23 | 甘雨由 付之笑 |
Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers, USENIX Security 2021 Face Forensics in the Wild, CVPR 2021 |
| 32 | 2021.7.30 | 邱鹏宇 卢令令 |
Improving Password Guessing via Representation Learning, IEEE S&P 2021 iQuery: Towards Trustworthy, Scalable Accountability for Blockchain-based IoT Payment System |
| 33 | 2021.8.6 | 梁红 陈安莹 |
TCP-Fuzz: Detecting Memory and Semantic Bugs in TCP Stacks with Fuzzing, USENIX ATC 2021 OSPREY: Recovery of Variable and Data Structure via Probabilistic Analysis for Stripped Binary, IEEE S&P 2021 |
| 34 | 2021.8.13 | 许嘉诚 侯黎阳 |
Automated Conformance Testing for JavaScript Engines via Deep Compiler Fuzzing, PLDI 2021 Industry Practice of Coverage-Guided Enterprise-Level DBMS Fuzzing, ICSE 2021 |
| 35 | 2021.8.20 | 虞楚尔 段宇萱 |
Poltergeist: Acoustic Adversarial Machine Learning against Cameras and Computer Vision, IEEE S&P 2021 Demodalizing Face Recognition with Synthetic Samples, AAAI 2021 |
| 36 | 2021.8.27 | 陈源 付之笑 |
Awakening the Web's Sleeper Agents: Misusing Service Workers for Privacy Leakage, NDSS 2021 Multi-attentional Deepfake Detection, CVPR 2021 |
| 37 | 2021.9.3 | 张耀 付丽嫆 |
Extracting Training Data from Large Language Models, USENIX Security 2021 “It’s the Company, the Government, You and I”: User Perceptions of Responsibility for Smart Home Privacy and Security, USENIX Security 2021 |
| 38 | 2021.9.10 | 施程辉 唐嘉蔚 |
Leakage of Dataset Properties in Multi-Party Machine Learning, USENIX Security 2021 Adversarial Examples for Hamming Space Search, IEEE Trans 2020 |
| 39 | 2021.9.17 | 卢令令 付冲 |
Dynamic Authenticated Index Structures for Outsourced Databases, SIGMOD 2006 Blind Backdoors in Deep Learning Models, arXiv 2020 |
| 40 | 2021.9.24 | 沈鹿嘉 向意 |
Systematic Evaluation of Privacy Risks of Machine Learning Models, USENIX Security 2021 Constraint-guided Directed Greybox Fuzzing, USENIX Security 2021 |
| 41 | 2021.10.1 | 邱鹏宇 刘丁豪 |
Subpopulation Data Poisoning Attacks, arXiv 2020 Static Detection of Unsafe DMA Accesses in Device Drivers, USENIX Security 2021 |
| 42 | 2021.10.8 | 马哲 王琴应 |
|
| 43 | 2021.10.15 | 唐嘉蔚 陈安莹 |
|
| 44 | 2021.10.22 | 甘雨由 付丽嫆 |
|
| 45 | 2021.10.29 | 付之笑 叶童 |
|
| 46 | 2021.11.5 | 陈源 侯黎阳 |
|
| 47 | 2021.11.12 | 甘雨由 张耀 |
|
| 48 | 2021.11.19 | 施程辉 虞楚尔 |
|
| 49 | 2021.11.26 | 卢令令 王琴应 |
|
| 50 | 2021.12.3 | 段宇萱 陈越尧 |
|
| 51 | 2021.12.10 | 沈鹿嘉 付冲 |
|
| 52 | 2021.12.17 | 梁红 陈源 |
|
| 53 | 2021.12.24 | 吕晨阳 杜天宇 |
|
| 54 | 2021.12.31 | 向意 马哲 |