Related papers: BinaryShield: Cross-Service Threat Intelligence in…

Coding agents and LLM-powered applications routinely send potentially sensitive content to cloud LLM APIs where it may be logged, retained, used for training, or subpoenaed. Existing privacy tooling focuses on network-level encryption and…

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our…

Numerous companies have started offering services based on large language models (LLM), such as ChatGPT, which inevitably raises privacy concerns as users' prompts are exposed to the model provider. Previous research on secure reasoning…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

The rapid adoption of open-source Large Language Models (LLMs) in offline and enterprise environments has introduced a largely unexamined security risk like susceptibility to adversarial phishing prompts under static safety configurations.…

When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk…

Fine-tuning large language models (LLMs) raises privacy concerns due to the risk of exposing sensitive training data. Federated learning (FL) mitigates this risk by keeping training samples on local devices, while facing the following…

An increasing number of companies have begun providing services that leverage cloud-based large language models (LLMs), such as ChatGPT. However, this development raises substantial privacy concerns, as users' prompts are transmitted to and…

As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a…

Security patch detection (SPD) is crucial for maintaining software security, as unpatched vulnerabilities can lead to severe security risks. In recent years, numerous learning-based SPD approaches have demonstrated promising results on…

The integration of large language models (LLMs) into electronic design automation (EDA) workflows has introduced powerful capabilities for RTL generation, verification, and design optimization, but also raises critical security concerns.…

Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…

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…

Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct feature sets. However, SL is susceptible to backdoor attacks,…

Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some seemingly benign data can inadvertently steer a model…

Online tracking is a widespread practice on the web with questionable ethics, security, and privacy concerns. While web tracking can offer personalized and curated content to Internet users, it operates as a sophisticated surveillance…

Mobile devices have access to personal, potentially sensitive data, and there is a growing number of applications that transmit this personally identifiable information (PII) over the network. In this paper, we present the AntShield system…

Wireless networks are vulnerable to jamming attacks due to the shared communication medium, which can severely degrade performance and disrupt services. Despite extensive research, current jamming detection methods often rely on simulated…

Directly releasing those data raises privacy and liability (e.g., due to unauthorized distribution of such datasets) concerns since location data contain users' sensitive information, e.g., regular moving patterns and favorite spots. To…

Recent progress in artificial intelligence (AI), particularly in the domain of large language models (LLMs), has resulted in powerful and versatile dual-use systems. This intelligence can be put towards a wide variety of beneficial tasks,…