Here's your daily roundup of the most relevant AI and ML news for August 06, 2026. Today's digest includes 3 security-focused stories. We're also covering 5 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. QuickFox Supply Chain Attack Delivers FDMTP Backdoor via Trojanized Windows Installer
Cybersecurity researchers have disclosed what has been described as a "long-standing supply chain attack" on QuickFox, a virtual private network (VPN) and network acceleration tool designed for overseas Chinese users.
According to Fortinet FortiGuard Labs, the supply chain attack has been ongoin...
Source: The Hacker News (Security) | 1 day ago
2. Poison Claude Sells Discounted Claude Access While Its Operator Sees Every Customer Prompt
Cybersecurity researchers have discovered more than half-a-dozen services advertisements for illegal access to artificial intelligence (AI) models on underground cybercrime forums and messaging platforms.
One such service, Poison Claude, claims to offer access to Anthropic's large language model...
Source: The Hacker News (Security) | 22 hours ago
3. AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory
A new class of prompt injection is spreading across commercial websites. It requires no malware, no stolen credentials, and no zero-day exploit. It abuses a standard feature built into almost every major AI assistant: pre-filled deep links.
We observed production websites embedding hidden prompt...
Source: The Hacker News (Security) | 2 hours ago
Research & Papers
4. AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection
arXiv:2608.04053v1 Announce Type: cross Abstract: Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcom...
Source: arXiv - AI | 10 hours ago
5. Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity
arXiv:2608.04045v1 Announce Type: new Abstract: Federated learning (FL) enables aircraft fleet operators to jointly train remaining-useful-life (RUL) models from engine sensor telemetry without sharing raw data. This study examines two complementary challenges: benign heterogeneity, where honest...
Source: arXiv - Machine Learning | 10 hours ago
6. Stabilizing Multi-Attack Adversarial Training via Bandit Optimization
arXiv:2511.12265v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) remain vulnerable to diverse adversarial perturbations, motivating multi-attack adversarial training (AT) for improved robustness. However, existing methods either incur prohibitive overhead by computing all attacks ...
Source: arXiv - Machine Learning | 10 hours ago
7. One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP
arXiv:2505.19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or rely on surrogate models closely mirroring the target mod...
Source: arXiv - Machine Learning | 10 hours ago
8. Dynamic Jailbreaking Attack
arXiv:2510.02422v4 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks typically optimize a fixed-length adversarial suffix toward a predefined target response with a static optimization strategy. However, this fully static formulation undermines the effectiveness, e...
Source: arXiv - AI | 10 hours ago
About This Digest
This digest is automatically curated from leading AI and tech news sources, filtered for relevance to AI security and the ML ecosystem. Stories are scored and ranked based on their relevance to model security, supply chain safety, and the broader AI landscape.
Want to see how your favorite models score on security? Check our model dashboard for trust scores on the top 500 HuggingFace models.