Related papers: Understanding Rowhammer Attacks through the Lens o…

RowHammer vulnerabilities pose a significant threat to modern DRAM-based systems, where rapid activation of DRAM rows can induce bit-flips in neighboring rows. To mitigate this, state-of-the-art host-side RowHammer mitigations typically…

Rowhammer is a well-studied DRAM phenomenon wherein multiple activations to a given row can cause bit flips in adjacent rows. Many mitigation techniques have been introduced to address Rowhammer, with some support being incorporated into…

Resistive random-access memory (RRAM) is gaining popularity due to its ability to offer computing within the memory and its non-volatile nature. The unique properties of RRAM, such as binary switching, multi-state switching, and device…

The Rowhammer vulnerability continues to get worse, with the Rowhammer Threshold (TRH) reducing from 139K activations to 4.8K activations over the last decade. Typical Rowhammer mitigations rely on tracking aggressor rows. The number of…

DRAM cells are susceptible to Data-Disturbance Errors (DDE), which can be exploited by an attacker to compromise system security. Rowhammer is a well-known DDE vulnerability that occurs when a row is repeatedly activated. Rowhammer can be…

Memory isolation is a critical property for system reliability, security, and safety. We demonstrate RowPress, a DRAM read disturbance phenomenon different from the well-known RowHammer. RowPress induces bitflips by keeping a DRAM row open…

LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks…

With lowering thresholds, transparently defending against Rowhammer within DRAM is challenging due to the lack of time to perform mitigation. Commercially deployed in-DRAM defenses like TRR that steal time from normal refreshes~(REF) to…

A decade after its academic introduction, RowHammer (RH) remains a moving target that continues to challenge both the industry and academia. With its potential to serve as a critical attack vector, the ever-decreasing RH threshold now…

The purpose of this document is to study the security properties of the Silver Bullet algorithm against worst-case RowHammer attacks. We mathematically demonstrate that Silver Bullet, when properly configured and implemented in a DRAM chip,…

Side-channel attacks on memory (SCAM) exploit unintended data leaks from memory subsystems to infer sensitive information, posing significant threats to system security. These attacks exploit vulnerabilities in memory access patterns, cache…

All the state-of-the-art rowhammer attacks can break the MMU-enforced inter-domain isolation because the physical memory owned by each domain is adjacent to each other. To mitigate these attacks, physical domain isolation, introduced by…

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains. Many prior studies have shown external attacks such as adversarial examples that…

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces…

Availability attacks, which poison the training data with imperceptible perturbations, can make the data \emph{not exploitable} by machine learning algorithms so as to prevent unauthorized use of data. In this work, we investigate why these…

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security…

Ransomware attacks have increased significantly in recent years, causing great destruction and damage to critical systems and business operations. Attackers are unfailingly finding innovative ways to bypass detection mechanisms,…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…