Related papers: PACT: Reducing Alert Fatigue in Low-Prevalence SOC…
Static code analysis (SCA) tools are widely used as effective ways to detect bugs and vulnerabilities in software systems. However, the reports generated by these tools often contain a large number of non-actionable findings, which can…
Towards predicting patch correctness in APR, we propose a simple, but novel hypothesis on how the link between the patch behaviour and failing test specifications can be drawn: similar failing test cases should require similar patches. We…
Pareto set learning (PSL) is an emerging paradigm in multi-objective optimization that trains neural networks to map preference vectors to Pareto optimal solutions. However, existing PSL methods primarily focus on solving a single…
Can a transformer learn which attention entries matter during training? In principle, yes: attention distributions are highly concentrated, and a small gate network can identify the important entries post-hoc with near-perfect accuracy. In…
As extended reality (XR) is redefining how users interact with computing devices, research in human action recognition is gaining prominence. Typically, models deployed on immersive computing devices are static and limited to their default…
Federated learning (FL) is vulnerable to backdoor attacks, yet most existing methods are limited by fixed-pattern or single-target triggers, making them inflexible and easier to detect. We propose FLAT (FL Arbitrary-Target Attack), a novel…
Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising approach has not yet enjoyed similarly widespread adoption…
Estimating the Conditional Average Treatment Effect (CATE) is often constrained by the high cost of obtaining outcome measurements, making active learning essential. However, conventional active learning strategies suffer from a fundamental…
CLIP has achieved impressive zero-shot performance after pre-training on a large-scale dataset consisting of paired image-text data. Previous works have utilized CLIP by incorporating manually designed visual prompts like colored circles…
With the evolution of 6G, semantic communication has emerged as a promising paradigm by prioritizing the delivery of task-relevant meaning over strict bit-level correctness. However, existing transport mechanisms still rely on explicit port…
Advanced Persistent Threat (APT) have grown increasingly complex and concealed, posing formidable challenges to existing Intrusion Detection Systems in identifying and mitigating these attacks. Recent studies have incorporated graph…
Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…
Along with the rapid evolution of mobile communication technologies, such as 5G, there has been a drastically increase in telecom fraud, which significantly dissipates individual fortune and social wealth. In recent years, graph mining…
Sequential user behavior modeling is pivotal for Click-Through Rate (CTR) prediction yet is hindered by three intrinsic bottlenecks: (1) the "Attention Sink" phenomenon, where standard Softmax compels the model to allocate probability mass…
The performance of active learning algorithms can be improved in two ways. The often used and intuitive way is by reducing the overall error rate within the test set. The second way is to ensure that correct predictions are not forgotten…
Static analysis is effective for discovering software vulnerabilities but notoriously suffers from incomplete source--sink specifications and excessive false positives (FPs). We present \textsc{AdaTaint}, an LLM-driven taint analysis…
The detection of advanced persistent threats (APTs) remains a crucial challenge due to their stealthy, multistage nature and the limited availability of realistic, labeled datasets for systematic evaluation. Synthetic dataset generation has…
Training large neural network (NN) models requires extensive memory resources, and Activation Compressed Training (ACT) is a promising approach to reduce training memory footprint. This paper presents GACT, an ACT framework to support a…
The practical usage of reinforcement learning agents is often bottlenecked by the duration of training time. To accelerate training, practitioners often turn to distributed reinforcement learning architectures to parallelize and accelerate…
There are many hurdles that prevent the replication of existing work which hinders the development of new activity classification models. These hurdles include switching between multiple deep learning libraries and the development of…