Related papers: LeftoverLocals: Listening to LLM Responses Through…

Large Language Models (LLMs) that can be deployed locally have recently gained popularity for privacy-sensitive tasks, with companies such as Meta, Google, and Intel playing significant roles in their development. However, the security of…

In this paper, we present that security threats coming with existing GPU memory management strategy are overlooked, which opens a back door for adversaries to freely break the memory isolation: they enable adversaries without any privilege…

Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models (LLMs). In this work, we introduce Spill The Beans, a novel application of cache side-channels to…

The rapid growth of memory and computation requirements of large language models (LLMs) has outpaced the development of hardware, hindering people who lack large-scale high-end GPUs from training or deploying LLMs. However, consumer-level…

Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have…

Graphic Processing Units (GPUs) have transcended their traditional use-case of rendering graphics and nowadays also serve as a powerful platform for accelerating ubiquitous, non-graphical rendering tasks. One prominent task is inference of…

Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…

Running language models in the browser presents a unique opportunity to build efficient, private, and portable AI applications, but requires contending with constrained memory availability and heterogeneous hardware targets. To realize this…

Geo-obfuscation serves as a location privacy protection mechanism (LPPM), enabling mobile users to share obfuscated locations with servers, rather than their exact locations. This method can protect users' location privacy when data…

The use of local memory is important to improve the performance of OpenCL programs. However, its use may not always benefit performance, depending on various application characteristics, and there is no simple heuristic for deciding when to…

Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks. However, the mechanisms underlying knowledge storage and memory access within their parameters remain…

Large Language Models (LLMs) enable a new ecosystem with many downstream applications, called LLM applications, with different natural language processing tasks. The functionality and performance of an LLM application highly depend on its…

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

Hardware peripherals such as GPUs and FPGAs are commonly available in server-grade computing to accelerate specific compute tasks, from database queries to machine learning. CSPs have integrated these accelerators into their infrastructure…

Conversational assistants are increasingly integrating long-term memory with large language models (LLMs). This persistence of memories, e.g., the user is vegetarian, can enhance personalization in future conversations. However, the same…

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak…

Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem…

Memory forensics is an effective methodology for analyzing living-off-the-land malware, including threats that employ evasion, obfuscation, anti-analysis, and steganographic techniques. By capturing volatile system state, memory analysis…

Large industrial systems that combine services and applications, have become targets for cyber criminals and are challenging from the security, monitoring and auditing perspectives. Security log analysis is a key step for uncovering…

We propose locally rewritable codes (LWC) for resistive memories inspired by locally repairable codes (LRC) for distributed storage systems. Small values of repair locality of LRC enable fast repair of a single failed node since the lost…