Related papers: InSpectre: Breaking and Fixing Microarchitectural …

Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private and potentially sensitive training data by repeatedly querying the network. In this work, we develop a novel network architecture that…

In this work, we focus on analyzing vulnerability of nonlinear dynamical control systems to stealthy false data injection attacks on sensors. We start by defining the stealthiness notion in the most general form where an attack is…

Increased connectivity and remote reprogrammability/reconfigurability features of embedded devices in current-day power systems (including interconnections between information technology -- IT -- and operational technology -- OT --…

Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive…

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…

Cache side channel attacks are increasingly alarming in modern processors due to the recent emergence of Spectre and Meltdown attacks. A typical attack performs intentional cache access and manipulates cache states to leak secrets by…

In big data systems, the infrastructure is such that large amounts of data are hosted away from the users. In such a system information security is considered as a major challenge. From a customer perspective, one of the big risks in…

Constant-time (CT) verification tools are commonly used for detecting potential side-channel vulnerabilities in cryptographic libraries. Recently, a new class of tools, called speculative constant-time (SCT) tools, has also been used for…

There exists a verification gap between formal protocol specifications and their actual implementations, which this work aims to bridge via monitoring for compliance to the formal specification. We instrument the networking and…

Critical and sophisticated cyberattacks often take multitudes of reconnaissance, exploitations, and obfuscation techniques to penetrate through well protected enterprise networks. The discovery and detection of attacks, though needing…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Model extraction is a growing concern for the security of AI systems. For deep neural network models, the architecture is the most important information an adversary aims to recover. Being a sequence of repeated computation blocks, neural…

Distributed Complex Event Processing (DCEP) is a paradigm to infer the occurrence of complex situations in the surrounding world from basic events like sensor readings. In doing so, DCEP operators detect event patterns on their incoming…

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term this phenomenon Structural Cognitive Overload (SCO), a byproduct of the contention between…

Future MPSoCs with 1000 or more processor cores on a chip require new means for resource-aware programming in order to deal with increasing imperfections such as process variation, fault rates, aging effects, and power as well as thermal…

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection…

A long-standing challenge is the design of chips resilient to faults and glitches. Both fine-grained gate diversity and coarse-grained modular redundancy have been used in the past. However, these approaches have not been well-studied under…

Modern microprocessors depend on speculative execution, creating vulnerabilities that enable transient execution attacks. Prior defenses target speculative data leakage but overlook false dependencies from partial address aliasing, where…

Speculative execution attacks undermine the security of constant-time programming, the standard technique used to prevent microarchitectural side channels in security-sensitive software such as cryptographic code. Constant-time code must…