Related papers: Rollback and Forking Detection for Trusted Executi…

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…

With the increasing integration of smart meters in electrical grids worldwide, detecting energy theft has become a critical and ongoing challenge. Artificial intelligence (AI)-based models have demonstrated strong performance in identifying…

Device-side Large Language Models (LLMs) have witnessed explosive growth, offering higher privacy and availability compared to cloud-side LLMs. During LLM inference, both model weights and user data are valuable, and attackers may even…

Large language models (LLMs) have significantly facilitated human life, and prompt engineering has improved the efficiency of these models. However, recent years have witnessed a rise in prompt engineering-empowered attacks, leading to…

Security Operations Centers (SOCs) face mounting operational challenges. These challenges come from increasing threat volumes, heterogeneous SIEM platforms, and time-consuming manual triage workflows. We present an end-to-end threat…

Enclaves have emerged as a particularly compelling primitive to implement trusted execution environments: strongly isolated sensitive user-mode processes in a largely untrusted software environment. While the threat models employed by…

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…

With the continuous evolution of computational devices, more and more applications are being executed remotely. The applications operate on a wide spectrum of devices, ranging from IoT nodes with low computational capabilities to large…

Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM…

Large language models (LLMs) deployed in user-facing applications require long-horizon consistency: the ability to remember prior interactions, respect user preferences, and ground reasoning in past events. However, contemporary memory…

Remote code disclosure attacks threaten embedded systems as they allow attackers to steal intellectual property or to find reusable code for use in control-flow hijacking attacks. Execute-only memory (XOM) prevents remote code disclosures,…

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…

In this work, we present an efficient secure multi-party computation MPC protocol that provides strong security guarantees in settings with dishonest majority of participants who may behave arbitrarily. Unlike the popular MPC implementation…

Source Code Model learn the proper embeddings from source codes, demonstrating significant success in various software engineering or security tasks. The recent explosive development of LLM extends the family of SCMs,bringing LLMs for code…

The development process of microcontroller firmware often involves multiple parties. In such a scenario, the Intellectual Property (IP) is not protected against adversarial developers which have unrestricted access to the firmware binary.…

Reliability has emerged as a key topic of interest for researchers around the world to detect and/or mitigate the side effects of decreasing transistor sizes, such as soft errors. Traditional solutions, like DMR and TMR, incur significant…

Authenticated data storage on an untrusted platform is an important computing paradigm for cloud applications ranging from big-data outsourcing, to cryptocurrency and certificate transparency log. These modern applications increasingly…

LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache,…

Recent advances in secure hardware technologies, such as Intel SGX or ARM TrustZone, offer an opportunity to substantially reduce the costs of Byzantine fault-tolerance by placing the program code and state within a secure enclave known as…

Runtime integrity measurements identify unexpected changes in operating systems and hypervisors during operation, enabling early detection of persistent threats. System Management Mode, a privileged x86 CPU mode, has the potential to…