Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- posterNovember 2023
Poster: Unveiling the Impact of Patch Placement: Adversarial Patch Attacks on Monocular Depth Estimation
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3639–3641https://doi.org/10.1145/3576915.3624400For autonomous driving systems, cameras and LiDAR sensors are necessary devices that provide precise depth information by which positions and sizes of objects can be identified. Moreover, recent advances in deep learning have extended their capabilities ...
- posterNovember 2023
Poster: Towards a Dataset for the Discrimination between Warranted and Unwarranted Emails
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3603–3605https://doi.org/10.1145/3576915.3624397In this research, the prevailing issue we address is the over-generalized perspective of spam/ham (non-spam) classification. Despite the intricacies of spam classification, reliance on user feedback may inadvertently skew filters to misclassify ...
- posterNovember 2023
Poster: RPAL-Recovering Malware Classifiers from Data Poisoning using Active Learning
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3561–3563https://doi.org/10.1145/3576915.3624391Intuitively, poisoned machine learning (ML) models may forget their adversarial manipulation via retraining. However, can we quantify the time required for model recovery? From an adversarial perspective, is a small amount of poisoning sufficient to ...
- posterNovember 2023
Poster: Query-efficient Black-box Attack for Image Forgery Localization via Reinforcement Learning
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3552–3554https://doi.org/10.1145/3576915.3624390Recently, deep learning has been widely used in forensics tools to detect and localize forgery images. However, its susceptibility to adversarial attacks highlights the need for the exploration of anti-forensics research. To achieve this, we introduce an ...
- posterNovember 2023
Poster: Multi-target & Multi-trigger Backdoor Attacks on Graph Neural Networks
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3570–3572https://doi.org/10.1145/3576915.3624387Recent research has indicated that Graph Neural Networks (GNNs) are vulnerable to backdoor attacks, and existing studies focus on the One-to-One attack where there is a single target triggered by a single backdoor. In this work, we explore two advanced ...
-
- posterNovember 2023
Poster: Mujaz: A Summarization-based Approach for Normalized Vulnerability Description
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3537–3539https://doi.org/10.1145/3576915.3624386This work proposes a multi-task Natural Language Processing (NLP) system to normalize and summarize the descriptions into a uniform structure. A dataset was curated from an official public database and broken into several constituent entities ...
- posterNovember 2023
Poster: Membership Inference Attacks via Contrastive Learning
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3555–3557https://doi.org/10.1145/3576915.3624384Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the training set data. Membership Inference Attacks (MIAs) exploit this feature ...
- posterNovember 2023
Poster: Generating Experiences for Autonomous Network Defense
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3531–3533https://doi.org/10.1145/3576915.3624381Reinforcement Learning (RL) offers a promising path toward developing defenses for the next generation of computer networks. The hope is that RL not only helps to automate network defenses, but in addition, RL finds novel solutions to defend networks ...
- posterNovember 2023
Poster: Fooling XAI with Explanation-Aware Backdoors
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3612–3614https://doi.org/10.1145/3576915.3624379The overabundance of learnable parameters in recent machine-learning models renders them inscrutable. Even their developers can not explain their exact inner workings anymore. For this reason, researchers have developed explanation algorithms to shed ...
- posterNovember 2023
Poster: Boosting Adversarial Robustness by Adversarial Pre-training
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3540–3542https://doi.org/10.1145/3576915.3624370Vision Transformer (ViT) shows superior performance on various tasks, but, similar to other deep learning techniques, it is vulnerable to adversarial attacks. Due to the differences between ViT and traditional CNNs, previous works designed new ...
- posterNovember 2023
Poster: Backdoor Attack on Extreme Learning Machines
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3588–3590https://doi.org/10.1145/3576915.3624369Deep neural networks (DNNs) achieve top performance through costly training on large datasets. Such resources may not be available in some scenarios, like IoT or healthcare. Extreme learning machines (ELMs) aim to alleviate this problem using single-...
- abstractNovember 2023
AISec '23: 16th ACM Workshop on Artificial Intelligence and Security
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3666–3668https://doi.org/10.1145/3576915.3624029The use of Artificial Intelligence (AI) and Machine Learning (ML) has been the center of the most outstanding advancements in the last years. The ability to analyze considerable streams of data in real time makes these technologies the most promising ...
- abstractNovember 2023
ARTMAN '23: First Workshop on Recent Advances in Resilient and Trustworthy ML Systems in Autonomous Networks
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3662–3663https://doi.org/10.1145/3576915.3624027The increasing integration of machine learning (ML) approaches into the operation and management (O&M) of modern networks has led researchers to address various problems such as performance optimization, anomaly detection, traffic prediction, root-cause ...
- research-articleNovember 2023
MESAS: Poisoning Defense for Federated Learning Resilient against Adaptive Attackers
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 1526–1540https://doi.org/10.1145/3576915.3623212Federated Learning (FL) enhances decentralized machine learning by safeguarding data privacy, reducing communication costs, and improving model performance with diverse data sources. However, FL faces vulnerabilities such as untargeted poisoning attacks ...
- research-articleNovember 2023
AntiFake: Using Adversarial Audio to Prevent Unauthorized Speech Synthesis
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 460–474https://doi.org/10.1145/3576915.3623209The rapid development of deep neural networks and generative AI has catalyzed growth in realistic speech synthesis. While this technology has great potential to improve lives, it also leads to the emergence of ''DeepFake'' where synthesized speech can be ...
- research-articleNovember 2023
Lanturn: Measuring Economic Security of Smart Contracts Through Adaptive Learning
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 1212–1226https://doi.org/10.1145/3576915.3623204We introduce Lanturn: a general purpose adaptive learning-based framework for measuring the cryptoeconomic security of composed decentralized-finance (DeFi) smart contracts. Lanturn discovers strategies comprising of concrete transactions for extracting ...
- research-articleNovember 2023
Experimenting with Zero-Knowledge Proofs of Training
- Sanjam Garg,
- Aarushi Goel,
- Somesh Jha,
- Saeed Mahloujifar,
- Mohammad Mahmoody,
- Guru-Vamsi Policharla,
- Mingyuan Wang
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 1880–1894https://doi.org/10.1145/3576915.3623202How can a model owner prove they trained their model according to the correct specification? More importantly, how can they do so while preserving the privacy of the underlying dataset and the final model? We study this problem and formulate the notion ...
- research-articleNovember 2023
A Good Fishman Knows All the Angles: A Critical Evaluation of Google's Phishing Page Classifier
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 2486–2500https://doi.org/10.1145/3576915.3623199Phishing is one of the most popular cyberspace attacks. Phishing detection has been integrated into mainstream browsers to provide online protection. The phishing detector of Google Chrome reports millions of phishing attacks per week. However, it has ...
- research-articleNovember 2023
Fait Accompli Committee Selection: Improving the Size-Security Tradeoff of Stake-Based Committees
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 845–858https://doi.org/10.1145/3576915.3623194We study the problem of committee selection in the context of proof-of-stake consensus mechanisms or distributed ledgers. These settings determine a family of participating parties---each of which has been assigned a non-negative ''stake''---and are ...
- research-articleNovember 2023
Abraxas: Throughput-Efficient Hybrid Asynchronous Consensus
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 519–533https://doi.org/10.1145/3576915.3623191Protocols for state-machine replication (SMR) often trade off performance for resilience to network delay. In particular, protocols for asynchronous SMR tolerate arbitrary network delay but sacrifice throughput/latency when the network is fast, while ...