Here's your daily roundup of the most relevant AI and ML news for March 17, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
arXiv:2602.02569v2 Announce Type: replace-cross Abstract: Fact-checking systems with search-enabled large language models (LLMs) have shown strong potential for verifying claims by dynamically retrieving external evidence. However, the robustness of such systems against adversarial attack remain...
Source: arXiv - AI | 10 hours ago
2. A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
arXiv:2603.06594v2 Announce Type: replace-cross Abstract: Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order ...
Source: arXiv - AI | 10 hours ago
3. Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
arXiv:2603.13424v1 Announce Type: cross Abstract: Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark (Greshake et al., 2024) against current generation models running inside OpenClaw, an open s...
Source: arXiv - AI | 10 hours ago
4. More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists
arXiv:2511.07112v2 Announce Type: replace-cross Abstract: When LLM agents work together, they seem to be more powerful than a single LLM in mathematical question answering. However, are they also more robust to adversarial inputs? We investigate this question using adversarially perturbed math q...
Source: arXiv - AI | 10 hours ago
5. ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving
arXiv:2603.15221v1 Announce Type: new Abstract: Deploying autonomous driving systems requires robustness against long-tail scenarios that are rare but safety-critical. While adversarial training offers a promising solution, existing methods typically decouple scenario generation from policy opti...
Source: arXiv - Machine Learning | 10 hours ago
6. Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise
arXiv:2603.15596v1 Announce Type: new Abstract: We study linear contextual bandits under adversarial corruption and heavy-tailed noise with finite $(1+\epsilon)$-th moments for some $\epsilon \in (0,1]$. Existing work that addresses both adversarial corruption and heavy-tailed noise relies on a ...
Source: arXiv - Machine Learning | 10 hours ago
7. On the Adversarial Transferability of Generalized "Skip Connections"
arXiv:2410.08950v2 Announce Type: replace Abstract: Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification performance on natural examples), we investigate and identify an i...
Source: arXiv - Machine Learning | 10 hours ago
8. Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
arXiv:2510.00517v2 Announce Type: replace Abstract: Differential Attention (DA) has been proposed as a refinement to standard attention, suppressing redundant or noisy context through a subtractive structure and thereby reducing contextual hallucination. While this design sharpens task-relevant ...
Source: arXiv - Machine Learning | 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.