相关论文: S2malloc: Statistically Secure Allocator for Use-A…

The growing use of third-party hardware accelerators (e.g., FPGAs, ASICs) for deep neural networks (DNNs) introduces new security vulnerabilities. Conventional model-level backdoor attacks, which only poison a model's weights to misclassify…

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…

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,…

We introduce the Lossy Implicit Network Activation Coding (LINAC) defence, an input transformation which successfully hinders several common adversarial attacks on CIFAR-$10$ classifiers for perturbations up to $\epsilon = 8/255$ in…

Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time reasoning, enabling them to recover obfuscated malicious intent during inference and refuse…

Machine learning (ML) based indoor localization solutions are critical for many emerging applications, yet their efficacy is often compromised by hardware/software variations across mobile devices (i.e., device heterogeneity) and the threat…

We initiate the study of adversarial attacks on models for binary (i.e. black and white) image classification. Although there has been a great deal of work on attacking models for colored and grayscale images, little is known about attacks…

Fault injection attacks are a potent threat against embedded implementations of neural network models. Several attack vectors have been proposed, such as misclassification, model extraction, and trojan/backdoor planting. Most of these…

Address Space Layout Randomization (ASLR) is a crucial defense mechanism employed by modern operating systems to mitigate exploitation by randomizing processes' memory layouts. However, the stark reality is that real-world implementations…

Label manipulation attacks are a subclass of data poisoning attacks in adversarial machine learning used against different applications, such as malware detection. These types of attacks represent a serious threat to detection systems in…

The primary function of memory allocators is to allocate and deallocate chunks of memory primarily through the malloc API. Many memory allocators also implement other API extensions, such as deriving the size of an allocated object from the…

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,…

Applications making excessive use of single-object based data structures (such as linked lists, trees, etc...) can see a drop in efficiency over a period of time due to the randomization of nodes in memory. This slow down is due to the…

Memory allocators hide beneath nearly every application stack, yet their performance footprint extends far beyond their code size. Even small inefficiencies in the allocators ripple through caches and the rest of the memory hierarchy,…

The multi-armed bandit formalism has been extensively studied under various attack models, in which an adversary can modify the reward revealed to the player. Previous studies focused on scenarios where the attack value either is bounded at…

Machine learning models are increasingly used in fields that require high reliability such as cybersecurity. However, these models remain vulnerable to various attacks, among which the adversarial label-flipping attack poses significant…

Code-reuse attacks have become a kind of common attack method, in which attackers use the existing code in the program to hijack the control flow. Most existing defenses focus on control flow integrity (CFI), code randomization, and…

Adversarial examples have gained tons of attention in recent years. Many adversarial attacks have been proposed to attack image classifiers, but few work shift attention to object detectors. In this paper, we propose Sparse Adversarial…

In the main text published at USENIX Security 2025, we presented a systematic analysis of the role of cache occupancy in the design considerations for randomized caches (from the perspectives of performance and security). On the performance…

Current adversarial attacks against speaker recognition systems (SRSs) require either white-box access or heavy black-box queries to the target SRS, thus still falling behind practical attacks against proprietary commercial APIs and…