Related papers: PICO: Secure Transformers via Robust Prompt Isolat…

While Secure Aggregation (SA) protects update confidentiality in Cross-silo Federated Learning, it fails to guarantee aggregation integrity, allowing malicious servers to silently omit or tamper with updates. Existing verifiable aggregation…

Current safety alignment methods encode safe behavior implicitly within model parameters, creating a fundamental opacity: we cannot easily inspect why a model refuses a request, nor intervene when its safety judgments fail. We propose Safe…

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing…

We propose a unified framework for deriving and studying soft-in-soft-out (SISO) detection in interference channels using the concept of variational inference. The proposed framework may be used in multiple-access interference (MAI),…

In this paper, we propose a novel safety-critical control framework for a chain of integrators subject to both matched and mismatched perturbations. The core of our approach is a linear, time-varying state-feedback design that…

The number of cyber-attacks have substantially increased over the past decade resulting in huge organizational financial losses. Indeed, it is no longer a matter of "if" but "when" a security incident will take place. A Security Operations…

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…

Security of model parameters and user data is critical for Transformer-based services, such as ChatGPT. While recent strides in secure two-party protocols have successfully addressed security concerns in serving Transformer models, their…

In this paper we consider the robust secure beamformer design for MISO wiretap channels. Assume that the eavesdroppers' channels are only partially available at the transmitter, we seek to maximize the secrecy rate under the transmit power…

Face recognition systems are increasingly used in biometric security for convenience and effectiveness. However, they remain vulnerable to spoofing attacks, where attackers use photos, videos, or masks to impersonate legitimate users. This…

Cache side channel attacks obtain victim cache line access footprint to infer security-critical information. Among them, cross-core attacks exploiting the shared last level cache are more threatening as their simplicity to set up and high…

As an important cyber-physical system (CPS), smart grid is highly vulnerable to cyber attacks. Amongst various types of attacks, false data injection attack (FDIA) proves to be one of the top-priority cyber-related issues and has received…

The Industrial Internet of Things (IIoT) has already become a part of our everyday life be it water supply, smart grid, or production, IIoT is everywhere. For example, factory operators want to know the current state of the production line.…

A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…

Security is an important facet of integrated circuit design for many applications. IP privacy and Trojan insertion are growing threats as circuit fabrication in advanced nodes almost inevitably relies on untrusted foundries. A proposed…

Hardware IP protection has been one of the most critical areas of research in the past years. Recently, attacks on hardware IPs (such as reverse engineering or cloning) have evolved as attackers have developed sophisticated techniques.…

SAFE is a clean-slate design for a highly secure computer system, with pervasive mechanisms for tracking and limiting information flows. At the lowest level, the SAFE hardware supports fine-grained programmable tags, with efficient and…

This letter focuses on the physical layer security over two-user multiple-input multiple-output (MIMO) non-orthogonal multiple access (NOMA) networks. A linear precoding technique is designed to ensure the confidentiality of the message of…

A security policy specifies a security property as the maximal information flow. A distributed system composed of interacting processes implicitly defines an intransitive security policy by repudiating direct information flow between…

Handling communication overhead in large-scale tensor-parallel training remains a critical challenge due to the dense, near-zero distributions of intermediate tensors, which exacerbate errors under frequent communication and introduce…