相关论文: Return-Oriented Programming on RISC-V

Many cybersecurity attacks rely on analyzing a binary executable to find exploitable sections of code. Code obfuscation is used to prevent attackers from reverse engineering these executables. In this work, we focus on control flow…

This work evaluates how well hardware-based approaches detect stack buffer overflow (SBO) attacks in RISC-V systems. We conducted simulations on the PULP platform and examined micro-architecture events using semi-supervised anomaly…

Hybrid Retrieval-Augmented Generation (RAG) pipelines combine vector similarity search with knowledge graph expansion for multi-hop reasoning. We show that this composition introduces a distinct security failure mode: a vector-retrieved…

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…

Ransomware core capability, unauthorized encryption, demands controls that identify and block malicious cryptographic activity without disrupting legitimate use. We present a probabilistic, risk-based access control architecture that…

Many design companies have gone fabless and rely on external fabrication facilities to produce chips due to increasing cost of semiconductor manufacturing. However, not all of these facilities can be considered trustworthy; some may inject…

Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g.,…

Remote Code Execution (RCE) exploits pose a significant threat to AI and ML systems, particularly in GPU-accelerated environments where the computational power of GPUs can be misused for malicious purposes. This paper focuses on RCE attacks…

Open-vocabulary object detectors (OVODs) unify vision and language to detect arbitrary object categories based on text prompts, enabling strong zero-shot generalization to novel concepts. As these models gain traction in high-stakes…

Logic Encryption is one of the most popular hardware security techniques which can prevent IP piracy and illegal IC overproduction. It introduces obfuscation by inserting some extra hardware into a design to hide its functionality from…

The MiG-V was designed for high-security applications and is the first commercially available logic-locked RISC-V processor on the market. In this context logic locking was used to protect the RISC-V processor design during the untrusted…

A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…

Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack…

Generative retrieval (GR) has emerged as a promising paradigm in recommendation systems by autoregressively decoding identifiers of target items. Despite its potential, current approaches typically rely on the next-token prediction schema,…

Integrated circuits (ICs) are essential to modern electronic systems, yet they face significant risks from physical reverse engineering (RE) attacks that compromise intellectual property (IP) and overall system security. While IC camouflage…

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…

Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abilities on complex logical tasks, such as mathematics and programming. However, we…

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adversarial attacks,…

The diffusion of fingerprint verification systems for security applications makes it urgent to investigate the embedding of software-based presentation attack detection algorithms (PAD) into such systems. Companies and institutions need to…

Ensuring safety in Reinforcement Learning (RL), typically framed as a Constrained Markov Decision Process (CMDP), is crucial for real-world exploration applications. Current approaches in handling CMDP struggle to balance optimality and…