3d-card (0.1.0), aamutils (>=0.0.11, <=0.0.12) +574 more potentially affected by CVE-2026-54058 via pillow (>=12.0.0, <=12.2.0)

pillow PYPI version =12.0.0, =0.0.11, =0.4.0, =1.10.0rc1, =0.0.116, =0.2.0, =0.1.1, =0.13.2, =0.1.0rc1, =0.1.0, =1.1.0, =1.3.0, =0.1.0, =0.2.0, =0.5.0 and more Source cves: CVE-2026-54058 Source advisory: GHSA-62P4-GMF7-7G93...

adversarial-robustness-toolbox (1.2.0), aristote-malo (1.9.5) +79 more potentially affected by CVE-2026-54058 via pillow (7.0.0)

pillow PYPI version 7.0.0 is affected by a known vulnerability. The following packages have a transitive dependency on pillow and may be impacted: - adversarial-robustness-toolbox 1.2.0 - aristote-malo 1.9.5 - auto-annotate =1.0.0, =1.0.2, =0.1.0.dev31, =1.0.1, =0.2.3, =0.0.1.25, =0.2.1, =0.0.2,...

Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT

Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them. Most reported detection accuracies, however, are measured on clean, in-distribution test data rather than on emails deliberately altered to evade detection. Th...

A Multi-Model Hybrid Defense Approach against White-Box Adversarial Attacks in Computer Network Traffic

It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System NIDS. However, NIDS faces a major security concern due to its...

Shared Vulnerabilities in Robustness-Optimized Defenses: One Breach Exposes the Family

Adversarial robustness optimization aims to preserve correct prediction under adversarial perturbations, and has produced substantial robustness gains through methods such as adversarial training and adversarial purification. However, we identify a new security risk: these gains can create shared...

OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol

OpenAI has disclosed details of GPT-Red , an internal automated red-teaming model that scales prompt injection vulnerability discovery with an aim to fix issues before the tools are deployed widely. "GPT‑Red is a strong red-teamer, and our previous models are highly vulnerable to its prompt...

Boundary-Seeking GAN-Augmented TabTransformer for Adversarially Robust Intrusion Detection

Machine learning-based intrusion detection systems IDSs often suffer from class imbalance and vulnerability to adversarial attacks, leading to degraded detection performance and reduced robustness. This study proposes a TabTransformer framework augmented by the Boundary-Seeking Generative...

Adversarial Prompting Framework for AI Safety Assessment

Artificial Intelligence AI, especially Generative AI GenAI, adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actors -- adversarial prompt attack APA being one of the mos...

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation

Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational controls to achieve security-relevant compromise. This paradigm remains necessary for AI-enabled systems, but it is no longer sufficient. In such...

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation

Large Language Models are increasingly deployed in Security Operations Centers for log analysis tasks including summarization, alert triage, and threat investigation. These systems ingest logs from external-facing services and process network logs as natural language contexts to generate security...

3d-card (0.1.0), aamutils (>=0.0.11, <=0.0.12) +574 more potentially affected by CVE-2026-59205 via pillow (>=12.0.0, <=12.2.0)

pillow PYPI version =12.0.0, =0.0.11, =0.4.0, =1.10.0rc1, =0.0.116, =0.2.0, =0.1.1, =0.13.2, =0.1.0rc1, =0.1.0, =1.1.0, =1.3.0, =0.1.0, =0.2.0, =0.5.0 and more Source cves: CVE-2026-59205 Source advisory: SNYK:PYTHON-PILLOW-17972376...

3d-card (0.1.0), aamutils (>=0.0.11, <=0.0.12) +574 more potentially affected by CVE-2026-59203 via pillow (>=12.0.0, <=12.2.0)

pillow PYPI version =12.0.0, =0.0.11, =0.4.0, =1.10.0rc1, =0.0.116, =0.2.0, =0.1.1, =0.13.2, =0.1.0rc1, =0.1.0, =1.1.0, =1.3.0, =0.1.0, =0.2.0, =0.5.0 and more Source cves: CVE-2026-59203 Source advisory: OSV:PYSEC-2026-3452...

When Binaries Talk Back: Representation-Confusion Attacks on LLM-Assisted Reverse Engineering

LLM-assisted reverse-engineering RE systems analyze strings, decompiler output, and tool reports derived from ttacker-controlled binaries. A binary can make data look like instructions or records from one origin look like independent evidence. We call such failures Representation-Confusion Attack...

SoK: Federated Learning for Intrusion Detection in Vehicular Networks

Modern vehicular networks face an expanding attack surface across internal Electronic Control Units ECUs and external Vehicle-to-Everything V2X communication. Federated Learning FL has emerged as a decentralized paradigm to deploy Intrusion Detection Systems IDS without compromising data privacy...

Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability

Large language models LLMs have transformed misinformation from a primarily content-centric problem into a broader ecosystem-level security challenge. When misused, LLMs create risks beyond false content generation, enabling attacks on the social contexts, evidence sources, retrieval corpora, and...

Statistically Undetectable Backdoors in Deep Neural Networks

We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box setting, meaning that the backdoored and honestly trained models are close in total variation distance, even given th...

Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions

Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these models remain vulnerable to backdoor attacks, where malicious fine-tuning data covertly implants unsafe behaviors. Despite advances in defensive...

Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks Via Universal and Transferable Adversarial HalluSquatting

The growing adoption of agentic LLM applications has introduced a new threat previously named as promptware. While prior work has established that adversaries can exploit direct channels to LLM applications to apply promptware under weak threat models, many applications do not provide any direct...

adversarial-insight-ml (0.1.0), aibench (>=0.0.2, <=0.0.5) +95 more potentially affected by CVE-2024-6345 via setuptools (68.0.0)

setuptools PYPI version 68.0.0 is affected by a known vulnerability. The following packages have a transitive dependency on setuptools and may be impacted: - adversarial-insight-ml 0.1.0 - aibench =0.0.2, =0.0.5.dev0, =0.1.18, =2.1.0, =1.22.0a0, =1.0.0, =0.7.27, =0.1.0, =7.0.0, =0.1.28, =0.1.29 a...

PYSEC-2026-2304

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structuredoutputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the stri...