Related papers: UNSAIL: Thwarting Oracle-Less Machine Learning Att…

The exponential adoption of machine learning (ML) is propelling the world into a future of distributed and intelligent automation and data-driven solutions. However, the proliferation of malicious data manipulation attacks against ML,…

Billions of people rely on essential utility and manufacturing infrastructures such as water treatment plants, energy management, and food production. Our dependence on reliable infrastructures makes them valuable targets for cyberattacks.…

Neural networks (NNs) are already deployed in hardware today, becoming valuable intellectual property (IP) as many hours are invested in their training and optimization. Therefore, attackers may be interested in copying, reverse…

Autonomous vehicles (AVs) rely on accurate trajectory prediction for safe navigation in diverse traffic environments, yet existing models struggle with long-tail scenarios-rare but safety-critical events characterized by abrupt maneuvers,…

Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisoning attacks. Prior backdoor defense strategies have primarily…

Existing power analysis techniques rely on strong adversary models with prior knowledge of the leakage or training data. We introduce side-channel analysis with unsupervised learning (SCAUL) that can recover the secret key without requiring…

Current semi-supervised learning (SSL) methods assume a balance between the number of data points available for each class in both the labeled and the unlabeled data sets. However, there naturally exists a class imbalance in most real-world…

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

How to identify the comprehensive comparable performance of various Intrusion Detection (ID) algorithms which are based on the Model Checking (MC) techniques? To address this open issue, we conduct some tests for the model-checking-based…

Large language model (LLM) agents increasingly issue API calls that mutate real systems, yet many current architectures pass stochastic model outputs directly to execution layers. We argue that this coupling creates a safety risk because…

Conventional semi-supervised learning (SSL) ideally assumes that labeled and unlabeled data share an identical class distribution, however in practice, this assumption is easily violated, as unlabeled data often includes unknown class data,…

We integrate contrastive learning (CL) with adversarial learning to co-optimize the robustness and accuracy of code models. Different from existing works, we show that code obfuscation, a standard code transformation operation, provides…

Industrial control systems are critical to the operation of industrial facilities, especially for critical infrastructures, such as refineries, power grids, and transportation systems. Similar to other information systems, a significant…

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…

Quantum circuits are the fundamental representation of quantum algorithms and constitute valuable intellectual property (IP). Multiple quantum circuit obfuscation (QCO) techniques have been proposed in prior research to protect quantum…

Cyber-physical systems (CPS) and Internet-of-Things (IoT) devices are increasingly being deployed across multiple functionalities, ranging from healthcare devices and wearables to critical infrastructures, e.g., nuclear power plants,…

Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely integrated into newer models' safety training. However, we…

Large language models (LLMs) used across enterprises often use proprietary models and operate on sensitive inputs and data. The wide range of attack vectors identified in prior research - targeting various software and hardware components…

Logging systems are an essential component of security systems and their security has been widely studied. Recently (2017) it was shown that existing secure logging protocols are vulnerable to crash attack in which the adversary modifies…