Related papers: OptiLeak: Efficient Prompt Reconstruction via Rein…

Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by…

Conjunctive Searchable Symmetric Encryption (CSSE) enables secure conjunctive searches over encrypted data. While leakage-abuse attacks (LAAs) against single-keyword SSE have been extensively studied, their extension to conjunctive queries…

We propose using reinforcement learning to address the challenges of discovering microarchitectural vulnerabilities, such as Spectre and Meltdown, which exploit subtle interactions in modern processors. Traditional methods like random…

Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversaries infer sensitive user inputs from shared entries, leading…

In the effort to learn from extensive collections of distributed data, federated learning has emerged as a promising approach for preserving privacy by using a gradient-sharing mechanism instead of exchanging raw data. However, recent…

The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To address this limitation, recent studies propose distributed LLM…

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…

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…

Large Language Models (LLMs) have shown remarkable capabilities, with optimizing their input prompts playing a pivotal role in maximizing their performance. However, while LLM prompts consist of both the task-agnostic system prompts and…

Large language models (LLMs) demonstrate considerable proficiency in numerous coding-related tasks; however, their capabilities in detecting software vulnerabilities remain limited. This limitation primarily stems from two factors: (1) the…

Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although streaming probes enable real-time monitoring, they still…

Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within a candidate document (i.e., jailbreak prompt attacks) can significantly alter an LLM's…

Federated Learning is a privacy preserving decentralized machine learning paradigm designed to collaboratively train models across multiple clients by exchanging gradients to the server and keeping private data local. Nevertheless, recent…

Minimizing computational overhead in time-series classification, particularly in deep learning models, presents a significant challenge due to the high complexity of model architectures and the large volume of sequential data that must be…

Large reasoning models such as DeepSeek-R1 and OpenAI o1 generate extended chains of thought spanning thousands of tokens, yet their integration with retrieval-augmented generation (RAG) remains fundamentally misaligned. Current RAG systems…

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

Large Multimodal Models (LMMs) excel in visual-language tasks by leveraging numerous visual tokens for fine-grained visual information, but this token redundancy results in significant computational costs. Previous research aimed at…

Developers using LLMs and LLM-based agents in their applications have provided plenty of anecdotal evidence that in-context-learning (ICL) is fragile. In this paper, we show that in addition to the quantity and quality of examples, the…

The capacity of large language models (LLMs) to generate honest, harmless, and helpful responses heavily relies on the quality of user prompts. However, these prompts often tend to be brief and vague, thereby significantly limiting the full…