Related papers: MOAT: Securely Mitigating Rowhammer with Per-Row A…

Residual cross-talk in superconducting qubit devices creates a security vulnerability for emerging quantum cloud services. We demonstrate a Clifford-only Quantum Rowhammer attack-using just X and CNOT gates-that injects faults on IBM's…

Research endeavors have been made in learning robust Multimodal Large Language Models (MLLMs) against jailbreak attacks. However, existing methods for improving MLLMs' robustness still face critical challenges: \ding{172} how to efficiently…

Large Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT) reasoning, yet also face safety issues similar to those of basic language models. In particular, while algorithms are designed to guide them to…

Security is a growing problem that needs hardware support. Memristors provide an alternative technology for hardware-supported security implementation. This paper presents a specific technique that utilizes the benefits of hybrid…

Instilling reasoning capabilities in large models (LMs) using reasoning training (RT) significantly improves LMs' performances. Thus Audio Reasoning Models (ARMs), i.e., audio LMs that can reason, are becoming increasingly popular. However,…

Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Channel hopping provides a defense mechanism against jamming attacks in large scale \ac{iot} networks.} However, a sufficiently powerful attacker may be able to learn the channel hopping pattern and efficiently predict the channel to jam.…

A fundamental assumption in software security is that memory contents do not change unless there is a legitimate deliberate modification. Classical fault attacks show that this assumption does not hold if the attacker has physical access.…

Rowhammer attacks that corrupt level-1 page tables to gain kernel privilege are the most detrimental to system security and hard to mitigate. However, recently proposed software-only mitigations are not effective against such kernel…

This paper investigates the anti-jamming performance of a cognitive radar under a partially observable Markov decision process (POMDP) model. First, we obtain an explicit expression for uncertainty of jammer dynamics, which paves the way…

State-of-the-art in-memory computation has recently emerged as the most promising solution to overcome design challenges related to data movement inside current computing systems. One of the approaches to performing in-memory computation is…

ARM is becoming more popular in desktops and data centers, opening a new realm in terms of security attacks against ARM. ARM has released Pointer Authentication, a new hardware security feature that is intended to ensure pointer integrity…

In advanced jamming, the adversary intentionally concentrates the available energy budget on specific critical components (e.g., pilot symbols, acknowledgement packets, etc.) to (i) increase the jamming effectiveness, as more targets can be…

A fundamental assumption in software security is that a memory location can only be modified by processes that may write to this memory location. However, a recent study has shown that parasitic effects in DRAM can change the content of a…

State-of-the-art DRAM read disturbance mitigations rely on the read disturbance threshold (RDT) (e.g., the number of aggressor row activations needed to induce the first read disturbance bitflip) to securely and performance- and…

Multi-armed bandit (MAB) problems are widely applied to online optimization tasks that require balancing exploration and exploitation. In practical scenarios, these tasks often involve multiple conflicting objectives, giving rise to…

Resistive Random Access Memory (RRAM) crossbar arrays are an attractive memory structure for emerging nonvolatile memory due to their high density and excellent scalability. Their ability to perform logic operations using RRAM devices makes…

Hardware supply-chain attacks are raising significant security threats to the boot process of multiprocessor systems. This paper identifies a new, prevalent hardware supply-chain attack surface that can bypass multiprocessor secure boot due…

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the…