BestHub
Sign in
Tagged articles
9 articles
Page 1 of 1
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
May 14, 2026 · Artificial Intelligence

Embodied AI Security Survey: A Multi‑Layer Framework for Risks, Attacks, and Defenses

This survey systematically reviews Embodied AI security, proposing a five‑layer taxonomy (perception, cognition, planning, action & interaction, agentic system) that organizes over 400 papers on attacks, defenses, and open challenges, and highlights overlooked vulnerabilities such as multimodal perception fusion and planning instability under jailbreak attacks.

AI securityEmbodied AIadversarial attacks
0 likes · 26 min read
Embodied AI Security Survey: A Multi‑Layer Framework for Risks, Attacks, and Defenses
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 11, 2026 · Artificial Intelligence

Random Parameter Pruning Boosts Transferable Targeted Attacks Across Model Architectures

The RaPA method introduces random parameter pruning during adversarial generation, creating diverse model variants that markedly increase the success rate of targeted transfer attacks across CNN and Transformer architectures, even against defended models and with higher computational budgets, as demonstrated on ImageNet‑compatible benchmarks.

CNNTransformeradversarial attacks
0 likes · 14 min read
Random Parameter Pruning Boosts Transferable Targeted Attacks Across Model Architectures
Data Party THU
Data Party THU
Nov 11, 2025 · Artificial Intelligence

Why Early Adversarial Attacks Still Beat Modern Ones: A Fair Transferability Study

This paper systematically evaluates 23 transferable adversarial attacks and 11 defenses on ImageNet, revealing that early methods like DI outperform many newer attacks when hyper‑parameters are fairly matched, that diffusion‑based defenses give a false sense of security, and that higher transferability often comes at the cost of reduced stealthiness.

ImageNetadversarial attacksdeep learning security
0 likes · 8 min read
Why Early Adversarial Attacks Still Beat Modern Ones: A Fair Transferability Study
AI Frontier Lectures
AI Frontier Lectures
Oct 29, 2025 · Artificial Intelligence

Why Early DI Attacks Outperform Modern Methods: A Systematic Study of Transferable Adversarial Images

This paper systematically evaluates 23 transferable adversarial attacks and 11 defenses on ImageNet, revealing that early DI attacks surpass newer methods when hyper‑parameters are fairly set, diffusion defenses offer false security, and higher transferability often reduces stealthiness, urging fair benchmarking and comprehensive metrics.

ImageNetadversarial attacksdeep learning robustness
0 likes · 7 min read
Why Early DI Attacks Outperform Modern Methods: A Systematic Study of Transferable Adversarial Images
OPPO Amber Lab
OPPO Amber Lab
Mar 28, 2024 · Information Security

What Security Challenges Will Shape Smart AI Terminals? Insights from the 2024 IEEE‑OPPO Pan‑Terminal Security Forum

The 2024 IEEE‑OPPO Pan‑Terminal Security Forum, held on March 29 at Xi'an Jiaotong University, gathers leading researchers to discuss AI, IoT, blockchain, and smart contract security, presenting cutting‑edge threats, defense strategies, and future technical capabilities for intelligent terminal products.

AI securityIoT securityadversarial attacks
0 likes · 10 min read
What Security Challenges Will Shape Smart AI Terminals? Insights from the 2024 IEEE‑OPPO Pan‑Terminal Security Forum
AntTech
AntTech
Dec 5, 2022 · Artificial Intelligence

Four AAAI‑23 Papers from Ant Security Lab on Adversarial 3D Point Clouds, GNN‑Based Anti‑Money Laundering, Spiking Neural Network Dynamic Graph Learning, and Differential‑Private Adaptive Clipping

Ant Security Lab reports four AAAI‑23 accepted papers that introduce PF‑Attack for transferable 3D adversarial point clouds, AMAP a GNN‑driven anti‑money‑laundering framework, SpikeNet a spiking‑neural‑network approach for efficient dynamic graph representation, and DP‑PSAC a per‑sample adaptive clipping method for differential privacy, each with experimental validation and expert commentary.

AAAI-23adversarial attacksdifferential privacy
0 likes · 18 min read
Four AAAI‑23 Papers from Ant Security Lab on Adversarial 3D Point Clouds, GNN‑Based Anti‑Money Laundering, Spiking Neural Network Dynamic Graph Learning, and Differential‑Private Adaptive Clipping
Meituan Technology Team
Meituan Technology Team
Jun 23, 2022 · Artificial Intelligence

Highlights of Six Meituan Papers Accepted at CVPR 2022

Meituan’s six CVPR 2022 papers advance computer vision by introducing a few‑sample model compression method, a language‑bridged video object segmentation approach, a single‑stage 3D visual grounding technique, a dynamic early‑exit image captioning system, a boosted black‑box adversarial attack, and a semi‑supervised video paragraph grounding framework.

3D groundingCVPR 2022Computer Vision
0 likes · 15 min read
Highlights of Six Meituan Papers Accepted at CVPR 2022
DataFunTalk
DataFunTalk
Jun 21, 2022 · Information Security

Trusted Traffic Governance and Anti‑Fraud Strategies Using Captcha

This talk explains how to use semantic-driven captcha mechanisms to classify and manage trusted versus untrusted traffic, detailing anti‑fraud strategies, flow identification, countermeasures against simulator and protocol cracking, and proactive updates to stay ahead of black‑market attacks.

CaptchaTraffic Classificationadversarial attacks
0 likes · 15 min read
Trusted Traffic Governance and Anti‑Fraud Strategies Using Captcha