PulseAugur
EN
LIVE 07:57:37
ENTITY AI training data poisoning

AI training data poisoning

PulseAugur coverage of AI training data poisoning — every cluster mentioning AI training data poisoning across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
4
18 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
11 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

3 day(s) with sentiment data

RECENT · PAGE 1/2 · 22 TOTAL
  1. COMMENTARY · CL_368050 ·

    AI Model Weights Vulnerable to Tampering and Code Execution

    The security of AI model weights is a growing concern, as model files can execute code upon loading. Threat actors can embed malicious code or backdoors within tampered weights, posing a significant risk to AI systems. …

  2. TOOL · CL_363705 ·

    AI security expert trains language model on laptop CPU, reveals security insights

    An AI security professional trained a language model on a personal laptop CPU using Andrej Karpathy's llama2.c implementation to better understand AI security vulnerabilities. This hands-on approach revealed insights in…

  3. TOOL · CL_342073 ·

    New defense tricks target backdoor attacks on face recognition systems

    Researchers have developed a set of practical defense mechanisms to protect deep learning-based face recognition systems from backdoor attacks. These methods aim to safeguard systems where training data might be comprom…

  4. COMMENTARY · CL_285668 ·

    LLMs and Data Poisoning Weaponized to Manufacture Consensus

    The article discusses how Large Language Models (LLMs) and data poisoning techniques are being used to manipulate public opinion and create a manufactured consensus. This manipulation is achieved by subtly altering trai…

  5. TOOL · CL_277276 ·

    New SAGE method cleans poisoned AI training data using verified examples

    A new research paper introduces SAGE, a method designed to identify and remove poisoned data from machine learning training sets. This approach leverages a small number of verified examples, including both clean and poi…

  6. RESEARCH · CL_236985 ·

    LLM Agents Face Expanded Security Risks from Prompt Injection to Multi-Agent Threats

    This article analyzes the security risks associated with LLM agents, highlighting that their increased capabilities lead to a larger attack surface compared to traditional LLMs. Key vulnerabilities include prompt inject…

  7. COMMENTARY · CL_236191 ·

    Creators use AI data poisoning; Neno develops Ambient AI

    Creators are employing "data poisoning" methods to safeguard their intellectual property from AI scrapers, marking a new phase in the conflict over digital content. Simultaneously, Neno is developing "Ambient AI" to aut…

  8. TOOL · CL_227068 ·

    New CamoDocs attack targets RAG models, evades defenses

    Researchers have developed a new data poisoning technique called CamoDocs, specifically targeting retrieval-augmented generation (RAG) language models. This method avoids direct query inclusion in poisoned documents, ma…

  9. TOOL · CL_159300 ·

    AI Security Training: Protecting Large Language Models from Cyberattacks

    The article discusses the growing threat of cyberattacks targeting Large Language Models (LLMs) and emphasizes the critical need for robust AI security practices. It outlines common LLM attacks such as prompt injection,…

  10. TOOL · CL_128602 ·

    Byzantine Failures Harm Generalization More Than Data Poisoning in Distributed Learning

    A new research paper titled "Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning" by Thomas Boudou explores the impact of different threat models on th…

  11. TOOL · CL_117886 ·

    New theory analyzes AI data poisoning in continual learning

    A new theoretical framework has been developed to analyze data poisoning attacks and defenses in continual learning (CL). Researchers framed the interaction between adversaries and defenders as an online zero-sum game, …

  12. TOOL · CL_117854 ·

    New latent class attack and detection method detailed in arXiv paper

    Researchers have developed a new data poisoning technique called a latent class attack, which introduces a novel, unknown class of data and mislabels it as a known class. This attack could be used to bypass AI-based sec…

  13. TOOL · CL_117646 ·

    Bilevel optimization framework detailed for Neural Architecture Search

    This paper provides a structured overview of Neural Architecture Search (NAS) by framing it as a bilevel optimization problem. It categorizes existing NAS methods into sampling-based and bilevel theory-based approaches.…

  14. COMMENTARY · CL_92663 ·

    LLM Security Threats Evolve Beyond Traditional Defenses

    The rapid integration of Large Language Models (LLMs) into various industries has introduced a new set of security challenges that traditional methods struggle to address. Key vulnerabilities include prompt injection, w…

  15. RESEARCH · CL_79509 ·

    New attack targets robot learning via world model vulnerabilities

    Researchers have identified a new vulnerability in robot learning pipelines that exploit world models. By injecting malicious prompts or compromising transition dynamics into seemingly safe datasets, attackers can creat…

  16. TOOL · CL_53715 ·

    New Cordyceps attack enables covert control of LLMs via data poisoning

    Researchers have developed a new data poisoning technique called Cordyceps, which enables covert control attacks on large language models (LLMs). Unlike previous methods that rely on fixed trigger phrases, Cordyceps tea…

  17. COMMENTARY · CL_47205 ·

    Data poisoning disrupts BigTech surveillance and AI training

    Data poisoning is a method to disrupt the data used by large technology companies for surveillance and AI training. This technique involves subtly altering or corrupting data inputs to mislead AI models. By introducing …

  18. TOOL · CL_45671 ·

    AI blueprint analysis poses hidden security risks

    A security analysis highlights the risks associated with AI systems that interpret engineering blueprints, such as those developed at Skoltech. These systems, which use multimodal models to read and analyze architectura…

  19. RESEARCH · CL_41642 ·

    AI Security and Observability Guides for 2026 Released

    The provided articles offer a comprehensive guide to AI application observability and security testing for the year 2026. They detail methods for identifying and mitigating unique AI security threats such as prompt inje…

  20. MEME · CL_37735 ·

    Video promotes data poisoning to disrupt AI systems

    A YouTube video advocates for data poisoning as a method to disrupt AI systems. The content suggests this approach as a form of resistance against the proliferation and capabilities of artificial intelligence.