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

Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, this memory mechanism also creates a practical security…

Robin Hood hashing is a variation on open addressing hashing designed to reduce the maximum search time as well as the variance in the search time for elements in the hash table. While the case of insertions only using Robin Hood hashing is…

A learned database system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or…

Embedded software is developed under the assumption that hardware execution is always correct. Fault attacks break and exploit that assumption. Through the careful introduction of targeted faults, an adversary modifies the control-flow or…

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a…

Memory hard functions (MHFs) are an important cryptographic primitive that are used to design egalitarian proofs of work and in the construction of moderately expensive key-derivation functions resistant to brute-force attacks. Broadly…

Return Oriented Programming (ROP) is a technique by which an attacker can induce arbitrary behavior inside a vulnerable program without injecting a malicious code. The continues failure of the currently deployed defenses against ROP has…

Memory isolation is critical for system reliability, security, and safety. Unfortunately, read disturbance can break memory isolation in modern DRAM chips. For example, RowHammer is a well-studied read-disturb phenomenon where repeatedly…

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…

Microarchitectural timing attacks exploit subtle timing variations caused by hardware behaviors to leak sensitive information. In this paper, we introduce MCHammer, a novel side-channel technique that leverages machine clears induced by…

The security of a computer system depends on OS kernel protection. It is crucial to reveal and inspect new attacks on kernel data, as these are used by hackers. The purpose of this paper is to continue research into attacks on dynamically…

This paper investigates secure low-cost in-DRAM trackers for mitigating Rowhammer (RH). In-DRAM solutions have the advantage that they can solve the RH problem within the DRAM chip, without relying on other parts of the system. However,…

Emerging non-volatile memory (NVM) technologies offer unique advantages in energy efficiency, latency, and features such as computing-in-memory. Consequently, emerging NVM technologies are considered an ideal substrate for computation and…

With the growing adoption of retrieval-augmented generation (RAG) systems, various attack methods have been proposed to degrade their performance. However, most existing approaches rely on unrealistic assumptions in which external attackers…

Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibited outputs. However, due to significant differences among…

Memory errors continue to be a critical concern for programs written in low-level programming languages such as C and C++. Many different memory error defenses have been proposed, each with varying trade-offs in terms of overhead,…

Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…