·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Theker just raised $85M to build the factory robot that doesn’t specialize in anything2h◆Jeff Bezos’s Prometheus raises $12B to build an ‘artificial general engineer’ for the physical world2h◆SpaceX officially prices shares at $135 in the largest IPO ever7h◆Our new community investments in Virginia support local jobs and expand energy affordability.7h◆SpaceX SPV investors won’t know their true holdings until post-IPO lock-ups lift7h◆Amazon’s data centers used 2.5 billion gallons of water last year10h◆Deezer’s new tool can identify AI music from Spotify, Apple Music, and others11h◆Pool’s new app turns your screenshots into something useful12h◆DoorDash’s new AI chatbot lets you order with prompts and photos13h◆Anthropic apologizes for invisible Claude Fable guardrails16h◆Google DeepMind is worried about what happens when millions of agents start to interact16h◆Deezer launches an AI music detector for other streaming services19h◆Opendoor’s India exit is fueling a bigger conversation about AI and outsourcing23h◆MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning23h◆Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!23h◆ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation23h◆Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions23h◆The Impossibility of Eliciting Latent Knowledge23h◆Mapping Scientific Literature with Large Language Models and Topic Modeling23h◆Grounding Computer Use Agents on Human Demonstrations23h◆Theker just raised $85M to build the factory robot that doesn’t specialize in anything2h◆Jeff Bezos’s Prometheus raises $12B to build an ‘artificial general engineer’ for the physical world2h◆SpaceX officially prices shares at $135 in the largest IPO ever7h◆Our new community investments in Virginia support local jobs and expand energy affordability.7h◆SpaceX SPV investors won’t know their true holdings until post-IPO lock-ups lift7h◆Amazon’s data centers used 2.5 billion gallons of water last year10h◆Deezer’s new tool can identify AI music from Spotify, Apple Music, and others11h◆Pool’s new app turns your screenshots into something useful12h◆DoorDash’s new AI chatbot lets you order with prompts and photos13h◆Anthropic apologizes for invisible Claude Fable guardrails16h◆Google DeepMind is worried about what happens when millions of agents start to interact16h◆Deezer launches an AI music detector for other streaming services19h◆Opendoor’s India exit is fueling a bigger conversation about AI and outsourcing23h◆MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning23h◆Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!23h◆ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation23h◆Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions23h◆The Impossibility of Eliciting Latent Knowledge23h◆Mapping Scientific Literature with Large Language Models and Topic Modeling23h◆Grounding Computer Use Agents on Human Demonstrations23h◆
Tag

#adversarial-attacks

4 articles tagged #adversarial-attacks

arxivMay 1

Let's Measure Information Step-by-Step: AI-Based Evaluation Beyond Vibes

arXiv:2508.05469v3 Announce Type: replace Abstract: We evaluate artificial intelligence (AI) systems without ground truth by exploiting a link between strategic gaming and information loss. Building on established information theory, we analyze which mechanisms resist adversarial manipulation. This

#information-theory#adversarial-attacks#machine-learningRead on arxiv →
arxivApr 16

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

arXiv:2509.25843v2 Announce Type: replace Abstract: Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstrates that models refusing harmful requests often comply when rephrase

#safety#alignment#jailbreakingRead on arxiv →
arxivApr 10

Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback

arXiv:2603.28281v2 Announce Type: replace Abstract: We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset $D$ of trajectory-preference tuples (each preference being an $n$-dimensio

#machine-learning#reinforcement-learning#robustnessRead on arxiv →
arxivApr 10bearish

CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models

arXiv:2604.06987v1 Announce Type: cross Abstract: Palmprint recognition is deployed in security-critical applications, including access control and palm-based payment, due to its contactless acquisition and highly discriminative ridge-and-crease textures. However, the robustness of deep palmprint re

#security#adversarial-attacks#computer-visionRead on arxiv →
HomeModelsNews