Related papers: Auditing Membership Leakages of Multi-Exit Network…

With the growing amount of cyber threats, the need for development of high-assurance cyber systems is becoming increasingly important. The objective of this paper is to address the challenges of modeling and detecting sophisticated network…

In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…

Privacy auditing provides empirical lower bounds on the differential privacy parameters of learning algorithms. Existing methods, however, require interventional access to the training pipeline, either to retrain multiple times or to…

Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…

The Lightning Network is a scaling solution for Bitcoin that promises to enable rapid and private payment processing. In Lightning, multi-hop payments are secured by utilizing Hashed Time-Locked Contracts (HTLCs) and encrypted on the…

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

Recent studies have discovered that large language models (LLM) may be ``fooled'' to output private information, including training data, system prompts, and personally identifiable information, under carefully crafted adversarial prompts.…

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…

Large language models have achieved remarkable capabilities, but their practical deployment is hindered by significant computational costs. While adaptive computation methods like early-exiting promise to reduce these costs, they introduce…

Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…

Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While attacks such as Membership Inference (MIA), Attribute Inference (AIA), Data Extraction…

Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has…

Identity leakage can emerge when independent databases are joined, even when each dataset is anonymized individually. While previous work focuses on post-join detection or complex privacy models, little attention has been given to simple,…

Modern multi-core processors share cache resources for maximum cache utilization and performance gains. However, this leaves the cache vulnerable to side-channel attacks, where timing differences in shared cache behavior are exploited to…

As power consumption from AI training and inference continues to increase, AI accelerators are being integrated directly into the CPU. Intel's Advanced Matrix Extensions (AMX) is one such example, debuting on the 4th generation Intel Xeon…

Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to…

Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against the uncompressed model; while the vulnerability of compressed…

Financial risk detection in Enterprise Resource Planning (ERP) systems is an important but underexplored application of machine learning. Published studies in this area tend to suffer from vague dataset descriptions, leakage-prone…

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…