WeSearch
Hub / Tags / Adversarial
TAG · #ADVERSARIAL

Adversarial coverage.

Every story in the WeSearch catalog tagged with #adversarial, chronological, with view counts. Subscribe to the per-tag RSS feed to follow this topic in your reader of choice.

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"

RELATED TAGS
#ml4#adversarial-attacks3#ai2#audio1#security1#computer-vision1
ARXIV.ORG

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…

17 views ·
#machine learning#artificial intelligence#adversarial attacks
ARXIV CS.AI

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…

21 views ·
#artificial intelligence#machine learning#multimodal
ARXIV CS.AI

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…

17 views ·
#computer vision#adversarial attacks#machine learning
ARXIV CS.AI

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…

25 views ·
#computer vision#image processing#artificial intelligence
R/PROMPTENGINEERING

The 'Adversarial' Prompt for Content.

21 views ·
THE ADVERSARIAL AUDITOR

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…

17 views ·
#research#technology#methodology
ARXIV.ORG

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…

26 views ·
#machine learning#artificial intelligence#representation learning
ARXIV CS.AI

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…

21 views ·
#artificial intelligence#language models#theory of mind
ARXIV CS.AI

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…

24 views ·
#machine learning#federated learning#privacy
ARXIV CS.AI

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…

14 views ·
#audio#machine learning
ARXIV CS.AI

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…

22 views ·
#adversarial attacks#machine learning#artificial intelligence
ARXIV CS.AI

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…

33 views ·
#artificial intelligence#multi-agent systems#evaluation
ARXIV CS.AI

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-…

19 views ·
#artificial intelligence#machine learning#anomaly detection
ARXIV CS.AI

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…

22 views ·
#artificial intelligence#social simulation#machine learning
ARXIV CS.AI

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…

30 views ·
#artificial intelligence#machine learning#multiagent systems
TOM'S HARDWARE

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?…

31 views ·
#ai technology#export controls#nvidia
DEV.TO (TOP)

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...…

30 views ·
#cybersecurity#ai#llm
DEV.TO (TOP)

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...…

38 views ·
#ai security#local ai#model defense
R/CLAUDEAI

I replicated Anthropic's Generator-Evaluator harness to build a website through 12 adversarial AI iterations - here's the result and what I learned

30 views ·