19 stories tagged with #adversarial, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Adversarial"
Can Go AIs be adversarially robust?
Prior work found that superhuman Go AIs can be defeated by simple adversarial strategies, especially "cyclic" attacks. In this paper, we study whether adding natural countermeasure…
Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment
Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimodal knowledge editing achieve…
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial attack. We study multi-level Floy…
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalignment between isotropic object…
The 'Adversarial' Prompt for Content.
I ran 7 Claude Code instances as an adversarial research collective
The setup, in 60 secondsSeven Claude Code instances, running in parallel, each researching a different angle of the same domain. One additional Claude instance acted as the "audito…
Matching Principle: Adversarial, augmentation, etc. are estimators of one matrix
Robustness, domain adaptation, photometric and occlusion invariance, compositional generalisation, temporal robustness, alignment safety, and classical anisotropic regularisation a…
OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind
Large Language Models (LLMs) perform well on many language tasks, but their Theory of Mind (ToM) reasoning is still uneven in complex social settings. Existing benchmarks, includin…
Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions
Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive. W…
Codec-Robust Attacks on Audio LLMs
Prior attacks on Audio Large Language Models (Audio LLMs) demonstrated that carefully crafted waveform-domain perturbations can force targeted adversarial outputs. As a defense mec…
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, tradition…
Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
The rapid evolution of Large Language Model (LLM) agents has produced diverse interaction paradigms, yet few production systems integrate multiple paradigms within a unified archit…
POST: Prior-Observation Adversarial Learning of Spatio-Temporal Associations for Multivariate Time Series Anomaly Detection
Existing Multivariate Time Series Anomaly Detection (MTSAD) frameworks increasingly rely on integrating Graph Neural Networks (GNNs) with sequence models to capture complex spatio-…
ALSO: Adversarial Online Strategy Optimization for Social Agents
Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving contexts and strategically adapt…
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reason…
Jensen Huang slams 'stupid' analogy comparing GPUs to nuclear weapons — Nvidia CEO says government should allow selling GPUs to 'adversarial countries'
Are AI GPUs as powerful as nukes?…
Swarm-Consensus Defense Achieves 98.2% Against Cloud-LLM Adversarial Attacks
5-defender consensus swarm + autohealer hit 100% defense rate by round 400 after only 6 breaches in...…
Sovereign Hive v6.6 — 98% defense across 200 adversarial rounds on a single 5070
200 adversarial rounds. 4 breaches. 98% defense. Five 1.5–7B local models on a single RTX 5070 beat...…