Related papers: BliMe Linter

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Transactional Lock Elision (TLE) uses Hardware Transactional Memory (HTM) to execute unmodified critical sections concurrently, even if they are protected by the same lock. To ensure correctness, the transactions used to execute these…

Membership inference (MI) attacks affect user privacy by inferring whether given data samples have been used to train a target learning model, e.g., a deep neural network. There are two types of MI attacks in the literature, i.e., these…

Commercial large language models are typically deployed as black-box API services, requiring users to trust providers to execute inference correctly and report token usage honestly. We present IMMACULATE, a practical auditing framework that…

In this paper, we describe an attack against one of the Oblivious-Transfer-based blind signatures scheme, proposed in [1]. An attacker with a primitive capability of producing specific-range random numbers, while exhibiting a partial MITM…

Many inference services based on large language models (LLMs) pose a privacy concern, either revealing user prompts to the service or the proprietary weights to the user. Secure inference offers a solution to this problem through secure…

Secure multiparty computation enables the joint evaluation of multivariate functions across distributed users while ensuring the privacy of their local inputs. This field has become increasingly urgent due to the exploding demand for…

LLM-integrated applications are vulnerable to prompt injection attacks, where an attacker contaminates the input to inject malicious instructions, causing the LLM to follow the attacker's intent instead of the original user's. Existing…

Today's software is bloated with both code and features that are not used by most users. This bloat is prevalent across the entire software stack, from operating systems and applications to containers. Containers are lightweight…

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Btrim is a fast and lightweight software to trim adapters and low quality regions in reads from ultra high-throughput next-generation sequencing machines. It also can reliably identify barcodes and assign the reads to the original samples.…

Cache template attacks demonstrated automated leakage of user input in shared libraries. However, for large binaries, the runtime is prohibitively high. Other automated approaches focused on cryptographic implementations and media software…

Bug severity prediction is a critical task in software engineering as it enables more efficient resource allocation and prioritization in software maintenance. While AI-based analyses and models significantly require access to extensive…

Training data is a critical and often proprietary asset in Large Language Model (LLM) development, motivating the use of data watermarking to embed model-transferable signals for usage verification. We identify low coverage as a vital yet…

Tool-use large language model (LLM) agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats,…

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…

Modern parallel filesystems such as Lustre are designed to provide high, scalable I/O bandwidth in response to growing I/O requirements; however, the bursty I/O characteristics of many data-intensive scientific applications make it…

WebAssembly's (Wasm) monolithic linear memory model facilitates memory corruption attacks that can escalate to cross-site scripting in browsers or go undetected when a malicious host tampers with a module's state. Existing defenses rely on…

Model merging is a widespread technology in large language models (LLMs) that integrates multiple task-specific LLMs into a unified one, enabling the merged model to inherit the specialized capabilities of these LLMs. Most task-specific…

Smart meter devices enable a better understanding of the demand at the potential risk of private information leakage. One promising solution to mitigating such risk is to inject noises into the meter data to achieve a certain level of…