Related papers: STBPU: A Reasonably Secure Branch Prediction Unit

Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent work has shown that it is highly vulnerable to poisoning-based backdoor attacks operating…

The confidentiality of trained AI models on edge devices is at risk from side-channel attacks exploiting power and electromagnetic emissions. This paper proposes a novel training methodology to enhance resilience against such threats by…

Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…

Integrated CPU-GPU architecture provides excellent acceleration capabilities for data parallel applications on embedded platforms while meeting the size, weight and power (SWaP) requirements. However, sharing of main memory between CPU…

Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial…

In this work we present the Secure Machine, SeM for short, a CPU architecture extension for secure computing. SeM uses a small amount of in-chip additional hardware that monitors key communication channels inside the CPU chip, and only acts…

Cache side channel attacks are increasingly alarming in modern processors due to the recent emergence of Spectre and Meltdown attacks. A typical attack performs intentional cache access and manipulates cache states to leak secrets by…

Security analysis is an essential activity in security engineering to identify potential system vulnerabilities and achieve security requirements in the early design phases. Due to the increasing complexity of modern systems, traditional…

The implementations of most hardened cryptographic libraries use defensive programming techniques for side-channel resistance. These techniques are usually specified as guidelines to developers on specific code patterns to use or avoid.…

Many recent papers have proposed novel electrical measurements or physical inspection technologies for defending printed circuit boards (PCBs) and printed circuit board assemblies (PCBAs) against tampering. As motivation, these papers…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where an attacker manipulates a small portion of the training data to implant hidden backdoors into the model. The compromised model behaves normally on clean samples but…

Spectre intrusions exploit speculative execution design vulnerabilities in modern processors. The attacks violate the principles of isolation in programs to gain unauthorized private user information. Current state-of-the-art detection…

This paper introduces Okapi, a new hardware/software cross-layer architecture designed to mitigate Transient Execution Side Channel attacks, including Spectre variants, in modern computing systems. Okapi provides a hardware basis for secure…

Edge AI inference is becoming prevalent thanks to the emergence of small yet high-performance microprocessors. This shift from cloud to edge processing brings several benefits in terms of energy savings, improved latency, and increased…

Recent research has revealed an ever-growing class of microarchitectural attacks that exploit speculative execution, a standard feature in modern processors. Proposed and deployed countermeasures involve a variety of compiler updates,…

In large-scale networks, communication links between nodes are easily injected with false data by adversaries. This paper proposes a novel security defense strategy from the perspective of attack detection scheduling to ensure the security…

Machine learning algorithms, however effective, are known to be vulnerable in adversarial scenarios where a malicious user may inject manipulated instances. In this work we focus on evasion attacks, where a model is trained in a safe…

Memory corruption vulnerabilities often enable attackers to take control of a target system by overwriting control-flow relevant data (such as return addresses and function pointers), which are potentially stored in close proximity of…

Most STM systems are poorly equipped to support libraries of concurrent data structures. One reason is that they typically detect conflicts by tracking transactions' read sets and write sets, an approach that often leads to false conflicts.…