相关论文: Understanding Rowhammer Attacks through the Lens o…

Ransomware represents a pervasive threat, traditionally countered at the operating system, file-system, or network levels. However, these approaches often introduce significant overhead and remain susceptible to circumvention by attackers.…

Adversarial attacks are a potential threat to machine learning models by causing incorrect predictions through imperceptible perturbations to the input data. While these attacks have been extensively studied in unstructured data like…

Networked control systems consist of distributed sensors and actuators that communicate via a wireless network. The use of an open wireless medium and unattended deployment leaves these systems vulnerable to intelligent adversaries whose…

Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows…

In this paper, we continue the line of work initiated by Boneh and Zhandry at CRYPTO 2013 and EUROCRYPT 2013 in which they formally define the notion of unforgeability against quantum adversaries specifically, for classical message…

Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this capability also introduces a new attack surface: memory poisoning, where adversaries can inject…

Memory corruption is a serious class of software vulnerabilities, which requires careful attention to be detected and removed from applications before getting exploited and harming the system users. Symbolic execution is a well-known method…

Eavesdropping attacks in inference systems aim to learn not the raw data, but the system inferences to predict and manipulate system actions. We argue that conventional information security measures can be ambiguous on the adversary's…

Cyber threat intelligence is one of the emerging areas of focus in information security. Much of the recent work has focused on rule-based methods and detection of network attacks using Intrusion Detection algorithms. In this paper we…

This paper summarizes our work on characterizing application memory error vulnerability to optimize datacenter cost via Heterogeneous-Reliability Memory (HRM), which was published in DSN 2014, and examines the work's significance and future…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

As quantum computing advances, Post-Quantum Cryptography (PQC) schemes are adopted to replace classical algorithms. Among them is the Stateless Hash-Based Digital Signature Algorithm (SLH-DSA) that was recently standardized by NIST and is…

We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification,…

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

In multi-hop wireless systems, the need for cooperation among nodes to relay each other's packets exposes them to a wide range of security attacks. A particularly devastating attack is the wormhole attack, where a malicious node records…

Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine…

Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated…

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

System passwords serve as critical credentials for user authentication and access control when logging into operating systems or applications. Upon entering a valid password, users pass verification to access system resources and execute…