Description

本日紹介した論文の一覧

• Against All Odds: Overcoming Typology, Script, and Language Confusion in
  Multilingual Embedding Inversion Attacks
  http://arxiv.org/abs/2408.11749v1

• Efficient Detection of Toxic Prompts in Large Language Models
  http://arxiv.org/abs/2408.11727v1

• CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical
  Researcher
  http://arxiv.org/abs/2408.11650v1

• Private Counting of Distinct Elements in the Turnstile Model and
  Extensions
  http://arxiv.org/abs/2408.11637v1

• Confidential Computing on Heterogeneous Systems: Survey and Implications
  http://arxiv.org/abs/2408.11601v1

• Large Language Models are Good Attackers: Efficient and Stealthy Textual
  Backdoor Attacks
  http://arxiv.org/abs/2408.11587v1

• Characterizing the Evolution of Psychological Tactics and Techniques
  Exploited by Malicious Emails
  http://arxiv.org/abs/2408.11586v1

• Characterizing the Evolution of Psychological Factors Exploited by
  Malicious Emails
  http://arxiv.org/abs/2408.11584v1

• Constructions of Efficiently Implementable Boolean functions Possessing
  High Nonlinearity and Good Resistance to Algebraic Attacks
  http://arxiv.org/abs/2408.11583v1

• Security Evaluation in Software-Defined Networks
  http://arxiv.org/abs/2408.11486v1

• A Practical Trigger-Free Backdoor Attack on Neural Networks
  http://arxiv.org/abs/2408.11444v1

• EEG-Defender: Defending against Jailbreak through Early Exit Generation
  of Large Language Models
  http://arxiv.org/abs/2408.11308v1

• Correlation Analysis of Adversarial Attack in Time Series Classification
  http://arxiv.org/abs/2408.11264v1

• Privacy-Preserving Data Management using Blockchains
  http://arxiv.org/abs/2408.11263v1

なお、ポッドキャスト内で紹介する内容は、各論文の概要を日本語で解説したもので、論文概要の著作権は論文著者に帰属します。