Related papers: A Leak-Resilient Dual Stack Scheme for Backward-Ed…

Gradient leakage attacks are considered one of the wickedest privacy threats in deep learning as attackers covertly spy gradient updates during iterative training without compromising model training quality, and yet secretly reconstruct…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…

Selective data protection is a promising technique to defend against the data leakage attack. In this paper, we revisit technical challenges that were neglected when applying this protection to real applications. These challenges include…

The absence of security and privacy measures between DNS recursive resolvers and authoritative nameservers has been exploited by both on-path and off-path attackers. Although numerous security proposals have been introduced in practice and…

A new framework for information hiding security, called topological-security, has been proposed in a previous study. It is based on the evaluation of unpredictability of the scheme, whereas existing notions of security, as stego-security,…

Layout camouflaging (LC) is a promising technique to protect chip design intellectual property (IP) from reverse engineers. Most prior art, however, cannot leverage the full potential of LC due to excessive overheads and/or their limited…

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing…

Superconducting qubits, while promising for scalability and long coherence times, contain more than two energy levels, and therefore are susceptible to errors generated by the leakage of population outside of the computational subspace.…

Split manufacturing (SM) and layout camouflaging (LC) are two promising techniques to obscure integrated circuits (ICs) from malicious entities during and after manufacturing. While both techniques enable protecting the intellectual…

Many cybersecurity attacks rely on analyzing a binary executable to find exploitable sections of code. Code obfuscation is used to prevent attackers from reverse engineering these executables. In this work, we focus on control flow…

Recent Searchable Symmetric Encryption (SSE) schemes enable secure searching over an encrypted database stored in a server while limiting the information leaked to the server. These schemes focus on hiding the access pattern, which refers…

The remarkable capabilities of Large Language Models (LLMs) have raised significant safety concerns, particularly regarding "jailbreak" attacks that exploit adversarial prompts to bypass safety alignment mechanisms. Existing defense…

This letter proposes a novel, fully distributed, transient-safe resilient secondary control strategies for AC microgrids, addressing unbounded false data injection (FDI) attacks on control input channels. Unlike existing methods that focus…

Globalization of IC manufacturing has led to increased security concerns, notably IP theft. Several logic locking techniques have been developed for protecting designs, but they typically display very large overhead, and are generally…

Realizing flow security in a concurrent environment is extremely challenging, primarily due to non-deterministic nature of execution. The difficulty is further exacerbated from a security angle if sequential threads disclose control…

Hardware caches are essential performance optimization features in modern processors to reduce the effective memory access time. Unfortunately, they are also the prime targets for attacks on computer processors because they are…

This paper addresses the security allocation problem in a networked control system under stealthy injection attacks. The networked system is comprised of interconnected subsystems which are represented by nodes in a digraph. An adversary…

To provide data and code confidentiality and reduce the risk of information leak from memory or memory bus, computing systems are enhanced with encryption and decryption engine. Despite massive efforts in designing hardware enhancements for…

Two-party split learning is a popular technique for learning a model across feature-partitioned data. In this work, we explore whether it is possible for one party to steal the private label information from the other party during split…

Fault tolerance overhead of high performance computing (HPC) applications is becoming critical to the efficient utilization of HPC systems at large scale. HPC applications typically tolerate fail-stop failures by checkpointing. Another…