Related papers: JIT Spraying and Mitigations
Selective data protection is a promising technique to defend against the data leakage attack. In this paper, we revisit technical challenges that were neglected when applying this protection to real applications. These challenges include…
Adversarial training (AT) is considered to be one of the most reliable defenses against adversarial attacks. However, models trained with AT sacrifice standard accuracy and do not generalize well to novel attacks. Recent works show…
In this paper, we introduce a formal notion of partial compliance, called Attack-resistance, of a computer program running together with a defense mechanism w.r.t a non-exploitability specification. In our setting, a program may contain…
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…
For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…
This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers…
Split learning and differential privacy are technologies with growing potential to help with privacy-compliant advanced analytics on distributed datasets. Attacks against split learning are an important evaluation tool and have been…
Any decentralised distributed network is particularly vulnerable to the Sybil attack wherein a malicious node masquerades as several different nodes, called Sybil nodes, simultaneously in an attempt to disrupt the proper functioning of the…
Although existing backdoor defenses have gained success in mitigating backdoor attacks, they still face substantial challenges. In particular, most of them rely on large amounts of clean data to weaken the backdoor mapping but generally…
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process,…
DRAM scaling has exacerbated the RowHammer vulnerability. To counter this, JEDEC recently introduced Per Row Activation Counting (PRAC) with the Alert Back-Off protocol as an optional DDR5 feature. While promising, PRAC requires per-row…
Agentic AI coding editors driven by large language models have recently become more popular due to their ability to improve developer productivity during software development. Modern editors such as Cursor are designed not just for code…
We address the problem of securing distributed storage systems against eavesdropping and adversarial attacks. An important aspect of these systems is node failures over time, necessitating, thus, a repair mechanism in order to maintain a…
Just-in-time (JIT) compilation coupled with code caching are widely used to improve performance in dynamic programming language implementations. These code caches, along with the associated profiling data for the hot code, however, consume…
LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs,…
Although ransomware has received broad attention in media and research, this evolving threat vector still poses a systematic threat. Related literature has explored their detection using various approaches leveraging Machine and Deep…
Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation---which is…
Speculative execution is an optimization technique that has been part of CPUs for over a decade. It predicts the outcome and target of branch instructions to avoid stalling the execution pipeline. However, until recently, the security…
Malware detectors based on deep learning (DL) have been shown to be susceptible to malware examples that have been deliberately manipulated in order to evade detection, a.k.a. adversarial malware examples. More specifically, it has been…
A new class of vulnerabilities related to speculative and out-of-order execution, fault-injection, and microarchitectural side channels rose to attention in 2018. The techniques behind the transient execution vulnerabilities were not new,…