Related papers: Oreo: Protecting ASLR Against Microarchitectural A…

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Open Radio Access Networks (ORAN) is a new architectural approach, having been proposed only a few years ago, and it is an expansion of the current Next Generation Radio Access Networks (NG-RAN) of 5G. ORAN aims to break this closed RAN…

Large Language Models (LLMs) can be misused to spread unwanted content at scale. Content watermarking deters misuse by hiding messages in content, enabling its detection using a secret watermarking key. Robustness is a core security…

Dynamic malware analysis executes the program in an isolated environment and monitors its run-time behaviour (e.g. system API calls) for malware detection. This technique has been proven to be effective against various code obfuscation…

The aim of this paper is to demonstrate the feasibility of authenticated throughput-efficient routing in an unreliable and dynamically changing synchronous network in which the majority of malicious insiders try to destroy and alter…

Application virtual memory footprints are growing rapidly in all systems from servers down to smartphones. To address this growing demand, system integrators are incorporating ever larger amounts of main memory, warranting rethinking of…

This is a comment on "RIO: Return Instruction Obfuscation for Bare-Metal IoT Devices with Binary Analysis". RIO prevents finding gadgets for Return-Oriented Programming attacks by encrypting return instructions. This paper shows flaws in…

ARM Memory Tagging Extension (MTE) is a new hardware feature introduced in ARMv8.5-A architecture, aiming to detect memory corruption vulnerabilities. The low overhead of MTE makes it an attractive solution to mitigate memory corruption…

Securing neural networks (NNs) against model extraction and parameter exfiltration attacks is an important problem primarily because modern NNs take a lot of time and resources to build and train. We observe that there are no…

Emerging 5G millimeter-wave and sub-6 GHz networks enable high-accuracy indoor localization, but security and privacy vulnerabilities pose serious challenges. In this paper, we identify and address threats including location spoofing and…

The rapid growth in both the scale and complexity of Android malware has driven the widespread adoption of machine learning (ML) techniques for scalable and accurate malware detection. Despite their effectiveness, these models remain…

Precise positioning is a key enabler for emerging 5G applications, from autonomous transport to industrial automation. Yet the open physical layer (PL) leaves standard positioning reference signals (PRSs) vulnerable to manipulation. This…

Memory errors continue to be a critical concern for programs written in low-level programming languages such as C and C++. Many different memory error defenses have been proposed, each with varying trade-offs in terms of overhead,…

The rise of machine-to-machine communications has rekindled the interest in random access protocols as a support for a massive number of uncoordinatedly transmitting devices. The legacy ALOHA approach is developed under a collision model,…

Adversarial testing of large language models (LLMs) is crucial for their safe and responsible deployment. We introduce a novel approach for automated generation of adversarial evaluation datasets to test the safety of LLM generations on new…

Shared processor caches are vulnerable to conflict-based side-channel attacks, where an attacker can monitor access patterns of a victim by evicting victim cache lines using cache-set conflicts. Recent mitigations propose randomized mapping…

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

Hardware aliasing occurs when the same logical address can access different physical memory locations. This is a problem for software on some embedded systems and more generally when hardware becomes faulty in irretrievable locations, such…

The last level cache is vulnerable to timing based side channel attacks because it is shared by the attacker and the victim processes even if they are located on different cores. These timing attacks evict the victim cache lines using small…

Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in the real world. Existing approaches for detecting OOD examples work well when evaluated on benign in-distribution and OOD samples. However,…