Qian Wang

Template attack on masking AES based on fault sensitivity analysis

2015

Fault Sensitivity Analysis (FSA) is an emerging fault based attack that utilizes the sensitive circuit delay information to retrieve keys. However, one of the major limitations of the existing FSA methods is that they are …

Learning privately: Privacy-preserving canonical correlation analysis for cross-media retrieval

2017

A massive explosion of various types of data has been triggered in the “Big Data” era. In big data systems, machine learning plays an important role due to its effectiveness in discovering hidden information and …

Privacy-Preserving Collaborative Model Learning: The Case of Word Vector Training

2018 · IEEE Transactions on Knowledge and Data Engineering

Nowadays, machine learning is becoming a new paradigm for mining hidden knowledge in big data. The collection and manipulation of big data not only create considerable values, but also raise serious privacy concerns. To protect …

SAFE: A General Secure and Fair Auction Framework for Wireless Markets With Privacy Preservation

2020 · IEEE Transactions on Dependable and Secure Computing

With the prosperity of wireless and mobile communications, the allocation of wireless resources, e.g., spectrum channels, femtocell access permissions, and resource blocks of D2D connections, has become a matter of great concern, which leads to …

When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP

2023 · SSRN Electronic Journal

Multi-task learning (MTL) aims at achieving a better model by leveraging data and knowledge from multiple tasks. However, MTL does not always work – sometimes negative transfer occurs between tasks, especially when aggregating loosely related …

FastTextDodger: Decision-Based Adversarial Attack Against Black-Box NLP Models With Extremely High Efficiency

2024 · IEEE Transactions on Information Forensics and Security

Recently, achieving query-efficient adversarial example attacks targeting black-box natural language models has attracted widespread attention from researchers. This task is considered difficult due to the discrete nature of texts, limited knowledge of the target model, …

Hijacking Attacks against Neural Networks by Analyzing Training Data

2024 · arXiv (Cornell University)

Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs. Backdoor …

Single-Step Support Set Mining for Realistic Few-Shot Image Classification

2024

Traditional few-shot learning (FSL) methods, often based on N-way K-shot classification, typically assume access to a large amount of labelled base classes and a class-balanced support set, which are not always feasible in real-world applications. …

PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have excelled in various tasks but are still vulnerable to jailbreaking attacks, where attackers create jailbreak prompts to mislead the model to produce harmful or offensive content. Current jailbreak methods either …

TransShard: A Dynamic Transaction-Aware Sharding Scheme for Account-Based Blockchain

2024 · IEEE Access

The poor scalability of blockchain technology restricts its application in large-scale networks. Sharding technology is viewed as the most promising on-chain solution to improving blockchain scalability. However, the high proportion of cross-shard transactions (TXs) and …

A Context-Aware User-Item Representation Learning for Item Recommendation

2019 · ACM Transactions on Information Systems

Both reviews and user-item interactions (i.e., rating scores) have been widely adopted for user rating prediction. However, these existing techniques mainly extract the latent representations for users and items in an independent and static manner. …