Related papers: DangKiller: Eliminating Dangling Pointers Efficien…
The ability to detect, in real-time, heavy hitters is beneficial to many network applications, such as DoS and anomaly detection. Through programmable languages as P4, heavy hitter detection can be implemented directly in the data-plane,…
Intrusion detection systems (IDS) reinforce cyber defense by autonomously monitoring various data sources for traces of attacks. However, IDSs are also infamous for frequently raising false positives and alerts that are difficult to…
Modern AI-powered Integrated Development Environments (AI-IDEs) are increasingly defined by an Agent-centric architecture, where an LLM-powered Agent is deeply integrated to autonomously execute complex tasks. This tight integration,…
Self-supervised and multimodal vision encoders learn strong visual representations that are widely adopted in downstream vision tasks and large vision-language models (LVLMs). However, downstream users often rely on third-party pretrained…
High-performance computing (HPC) requires resilience techniques such as checkpointing in order to tolerate failures in supercomputers. As the number of nodes and memory in supercomputers keeps on increasing, the size of checkpoint data also…
Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and…
Deep neural networks (DNNs) are of critical use in different domains. To accelerate DNN computation, tensor compilers are proposed to generate efficient code on different domain-specific accelerators. Existing tensor compilers mainly focus…
Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings…
Despite decades of efforts to resolve, memory safety violations are still persistent and problematic in modern systems. Various defense mechanisms have been proposed, but their deployment in real systems remains challenging because of…
Sensitive information is present on our phones, disks, watches and computers. Its protection is essential. Plausible deniability of stored data allows individuals to deny that their device contains a piece of sensitive information. This…
Large-scale machine learning and data mining methods routinely distribute computations across multiple agents to parallelize processing. The time required for the computations at the agents is affected by the availability of local resources…
Many terminals are used in safety-critical operations in which humans, through terminal user interfaces, become a part of the system control loop (e.g., medical and industrial systems). These terminals are typically embedded, single-purpose…
Customized hardware accelerators have been developed to provide improved performance and efficiency for DNN inference and training. However, the existing hardware accelerators may not always be suitable for handling various DNN models as…
Backdoor attacks embed hidden associations between triggers and targets in deep neural networks (DNNs), causing them to predict the target when a trigger is present while maintaining normal behavior otherwise. Physical backdoor attacks,…
We present a highly compact run-time monitoring approach for deep computer vision networks that extracts selected knowledge from only a few (down to merely two) hidden layers, yet can efficiently detect silent data corruption originating…
Inference-time scaling has proven effective in boosting large language model (LLM) performance through increased test-time computation. Yet, its practical application is often hindered by reliance on external verifiers or a lack of…
Machine learning (ML)-based intrusion detection systems (IDSs) play a critical role in discovering unknown threats in a large-scale cyberspace. They have been adopted as a mainstream hunting method in many organizations, such as financial…
The growing security threat of microarchitectural attacks underlines the importance of robust security sensors and detection mechanisms at the hardware level. While there are studies on runtime detection of cache attacks, a generic model to…
Network-based intrusion detection system (NIDS) monitors network traffic for malicious activities, forming the frontline defense against increasing attacks over information infrastructures. Although promising, our quantitative analysis…
Windows malware detectors based on machine learning are vulnerable to adversarial examples, even if the attacker is only given black-box query access to the model. The main drawback of these attacks is that: (i) they are query-inefficient,…