Related papers: BreakHammer: Enhancing RowHammer Mitigations by Ca…

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with…

Major chip manufacturers have all introduced multicore microprocessors. Multi-socket systems built from these processors are routinely used for running various server applications. Depending on the application that is run on the system,…

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…

Deep learning-based recommendation models (DLRMs) are widely deployed in commercial applications to enhance user experience. However, the large and sparse embedding layers in these models impose substantial memory bandwidth bottlenecks due…

The widespread adoption of thinking mode in large language models (LLMs) has significantly enhanced complex task processing capabilities while introducing new security risks. When subjected to jailbreak attacks, the step-by-step reasoning…

Malicious attacks such as jamming can cause significant disruption or complete denial of service (DoS) to wireless communication protocols. Moreover, jamming devices are getting smarter, making them difficult to detect. Forward error…

Unsafe memory accesses in programs written using popular programming languages like C/C++ have been among the leading causes for software vulnerability. Prior memory safety checkers such as SoftBound enforce memory spatial safety by…

Large persistent memories such as NVDIMM have been perceived as a disruptive memory technology, because they can maintain the state of a system even after a power failure and allow the system to recover quickly. However, overheads incurred…

Many hardware structures in today's high-performance out-of-order processors do not scale in an efficient way. To address this, different solutions have been proposed that build execution schedules in an energy-efficient manner. Issue time…

Network slicing is a pivotal paradigm in wireless networks enabling customized services to users and applications. Yet, intelligent jamming attacks threaten the performance of network slicing. In this paper, we focus on the security aspect…

System prompts are widely used to guide the outputs of large language models (LLMs). These prompts often contain business logic and sensitive information, making their protection essential. However, adversarial and even regular user queries…

Hyperscalars run services across a large fleet of servers, serving billions of users worldwide. These services, however, behave differently than commonly available benchmark suites, resulting in server architectures that are not optimized…

Although ransomware has received broad attention in media and research, this evolving threat vector still poses a systematic threat. Related literature has explored their detection using various approaches leveraging Machine and Deep…

DRAM manufacturers have been prioritizing memory capacity, yield, and bandwidth for years, while trying to keep the design complexity as simple as possible. DRAM chips do not carry out any computation or other important functions, such as…

With the increasing use of multicore platforms to realize mixed-criticality systems, understanding the underlying shared resources, such as the memory hierarchy shared among cores, and achieving isolation between co-executing tasks running…

Use-After-Free vulnerabilities, allowing the attacker to access unintended memory via dangling pointers, are more threatening. However, most detection schemes can only detect dangling pointers and invalid them, but not provide a tolerance…

Binary program analysis represents a fundamental pillar of modern system security. Fine-grained methodologies like dynamic taint analysis still suffer from deployment complexity and performance overhead despite significant progress.…

Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the model training and private data provider are always separated,…

Embedded and Internet-of-Things (IoT) devices play a critical role in modern life. Their software and firmware, often developed in memory-unsafe languages like C, are susceptible to memory safety vulnerabilities that can lead to…

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…