Related papers: Mitigating Speculation-based Attacks through Confi…
Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on…
Speculative decoding is an effective method for lossless acceleration of large language models during inference. It uses a fast model to draft a block of tokens which are then verified in parallel by the target model, and provides a…
CySecTool is a tool that finds a cost-optimal security controls portfolio in a given budget for a probabilistic attack graph. A portfolio is a set of counter-measures, or controls, against vulnerabilities adopted for a computer system,…
The increasing sophistication of modern cyber threats, particularly file-less malware relying on living-off-the-land techniques, poses significant challenges to traditional detection mechanisms. Memory forensics has emerged as a crucial…
The hardware computing landscape is changing. What used to be distributed systems can now be found on a chip with highly configurable, diverse, specialized and general purpose units. Such Systems-on-a-Chip (SoC) are used to control today's…
Anticipating the strategies of potential attackers is crucial for protecting critical infrastructure. We can represent the challenge of the defenders of such infrastructure as a Stackelberg security game. The defender must decide how to…
Fault-tolerant routing (FTR) in Networks-on-Chip (NoCs) has become a common practice to sustain the performance of multi-core systems with an increasing number of faults on a chip. On the other hand, usage of third-party intellectual…
Analyzing the behavior of a program running on a processor that supports speculative execution is crucial for applications such as execution time estimation and side channel detection. Unfortunately, existing static analysis techniques…
Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting…
Today, security threats to operating systems largely come from network. Traditional discretionary access control mechanism alone can hardly defeat them. Although traditional mandatory access control models can effectively protect the…
CPU caches introduce variations into the execution time of programs that can be exploited by adversaries to recover private information about users or cryptographic keys. Establishing the security of countermeasures against this threat…
Ensuring constraint satisfaction is a key requirement for safety-critical systems, which include most robotic platforms. For example, constraints can be used for modeling joint position/velocity/torque limits and collision avoidance.…
Constant-time programming is a widely deployed approach to harden cryptographic programs against side channel attacks. However, modern processors often violate the underlying assumptions of standard constant-time policies by transiently…
Attackers can access sensitive information of programs by exploiting the side-effects of speculatively-executed instructions using Spectre attacks. To mitigate theses attacks, popular compilers deployed a wide range of countermeasures. The…
Speculative decoding enables collaborative Large Language Model (LLM) inference across cloud and edge by separating lightweight token drafting from heavyweight verification. While prior systems show performance and cost benefits, practical…
State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x more inference-time…
Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive…
As edge computing and the Internet of Things (IoT) expand, horizontal collaboration (HC) emerges as a distributed data processing solution for resource-constrained devices. In particular, a convolutional neural network (CNN) model can be…
We introduce explicit speculation, a variant of I/O speculation technique where I/O system calls can be parallelized under the guidance of explicit application code knowledge. We propose a formal abstraction -- the foreaction graph -- which…
Cyber attacks and malware are now more prevalent than ever and the trend is ever upward. There have been several approaches to attack detection including resident software applications at the root or user level, e.g., virus detection, and…