Skip to content

Category

cybersecurity

1,065 papers

#artificial intelligence Preprint Open access Sep 2026

CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration

Deep neural networks (DNNs) rely heavily on high-quality open-source datasets (e.g., ImageNet) for their success, making dataset ownership verification (DOV) crucial for protecting public dataset copyrights. In this paper, we find existing DOV methods (implicitly) assume that the verification process is faithful, where...

Ting Qiao, Yiming Li, Jianbin Li et al. · 0 citations
#machine learning Preprint Open access Sep 2026

DNA: Differentially private Neural Augmentation for contact tracing

The COVID19 pandemic had enormous economic and societal consequences. Contact tracing is an effective way to reduce infection rates by detecting potential virus carriers early. However, this was not generally adopted in the recent pandemic, and privacy concerns are cited as the most important reason. We substantially i...

Rob Romijnders, Christos Louizos, Yuki M. Asano et al. · 0 citations
#machine learning Preprint Sep 2026

Empirical Evaluation of Data Poisoning Attacks in Supervised Learning

The results separate indiscriminate poisoning, which shows up in standard metrics, from targeted backdoor poisoning, which stays comparatively stealthy while embedding highly effective malicious behavior, and they support security-oriented evaluation beyond conventional clean-test metrics.

T. Khan, Muhammad Abusaqer · 0 citations
#machine learning Preprint Sep 2026

Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2

Membership inference attacks (MIAs) try to determine whether a specific record was used to train a model, a privacy risk that matters in natural language processing (NLP), where training data can contain sensitive user text. This paper presents a controlled benchmark of membership inference vulnerability for text class...

W. Novak, Muhammad Abusaqer · 0 citations
#artificial intelligence Preprint Sep 2026

DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents

DriftNet is presented, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection).

Asif Pinjari, Mithun Paul Saint-Germain · 0 citations
#machine learning Preprint Sep 2026

Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models

When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the sentence was in its training data. Almost every published test of that inference has had to guess which sentences were in the training data, the members, and which were not. This paper removes the guessing. Two model...

Arman Nik Khah · 0 citations
#artificial intelligence Preprint Open access Sep 2026

Temporal and Multimodal Deep Learning for Cyberattack Detection in LEO Satellite Systems

The growing reliance on Low-Earth Orbit (LEO) satellite communication systems has increased the need for intelligent methods capable of detecting cyberattacks across complex and dynamic space environments. Unlike conventional network intrusion detection, satellite systems generate heterogeneous information across radio...

Kyle Stein, Guillermo Francia III, Eman El-Sheikh et al. · 0 citations
#artificial intelligence Preprint Sep 2026

CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding

Autoregressive language models can be used to transform a payload text into a stegotext of identical token length by preserving per-position rank information across contexts - a methodology we formalize as Contextual Autoregressive Rank Transcoding Steganography (CARTS). While the Calgacus construction of Norelli et al...

Wissam Ghantous, Alexander V. Mantzaris · 0 citations
#machine learning Preprint Open access Sep 2026

From Cycle Space to Cycle Manifold: Limits and Achievability of Blind False Data Injection Attacks

A false data injection attack (FDIA) can change the estimated grid state while evading a residual-based bad data detector (BDD). Existing blind attacks learn a low-rank measurement subspace, but this algebraic view does not state the physical grid constraints that make an attack stealthy or the minimum information need...

Xin Li, Chenhan Xiao, Jonathan Cohen et al. · 0 citations
#machine learning Preprint Sep 2026

SoK: Privacy Attacks on Machine Learning via Explainable AI

It is argued that explanation privacy should be evaluated as an end-to-end disclosure problem, with defenses matched to the acquisition path and protected asset, with defenses matched to the acquisition path and protected asset.

A. Oksuz, Anisa Halimi, Erman Ayday · 0 citations
#machine learning Preprint Sep 2026

Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting

Preliminary reweighting is established as a unifying and predictive framework for understanding and mitigating ICL jailbreak in MLLMs and a posterior-aware inference-time defense is introduced that adaptively injects benign counter-evidence based on estimated risk, effectively suppressing harmful posterior drift while...

Xu Zhang, Deven Mahesh Mistry, Xiang Xu et al. · 0 citations

From tech blogs

See all →
Google DeepMind Blog Jul 17, 2026

Introducing Gemini 3.5 Flash Cyber

Google introduces Gemini 3.5 Flash Cyber, a lightweight cybersecurity model to find and patch vulnerabilities.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.