Category: academic papers

Auto Added by WPeMatico

Applying Security Engineering to Prompt Injection Security

Posted on By infossl
academic papers, AI, google, LLM, security engineering, Security technology, Uncategorized

This seems like an important advance in LLM security against prompt injection: Google DeepMind has unveiled CaMeL (CApabilities for MachinE Learning), a new approach to stopping prompt-injection attacks that abandons the failed strategy of having AI models police themselves. Instead, CaMeL treats language models as fundamentally untrusted components within a secure software framework, creating clear … Read More “Applying Security Engineering to Prompt Injection Security” »

Regulating AI Behavior with a Hypervisor

Posted on By infossl
academic papers, AI, physical security, Security technology, threat models, Uncategorized

Interesting research: “Guillotine: Hypervisors for Isolating Malicious AIs.” Abstract:As AI models become more embedded in critical sectors like finance, healthcare, and the military, their inscrutable behavior poses ever-greater risks to society. To mitigate this risk, we propose Guillotine, a hypervisor architecture for sandboxing powerful AI models—models that, by accident or malice, can generate existential threats … Read More “Regulating AI Behavior with a Hypervisor” »

AIs as Trusted Third Parties

Posted on By infossl
academic papers, AI, cryptography, machine learning, Security technology, trust, Uncategorized

This is a truly fascinating paper: “Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography.” The basic idea is that AIs can act as trusted third parties: Abstract: We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private … Read More “AIs as Trusted Third Parties” »

Friday Squid Blogging: A New Explanation of Squid Camouflage

Posted on By infossl
academic papers, Security technology, squid, Uncategorized

New research: An associate professor of chemistry and chemical biology at Northeastern University, Deravi’s recently published paper in the Journal of Materials Chemistry C sheds new light on how squid use organs that essentially function as organic solar cells to help power their camouflage abilities. As usual, you can also use this squid post to … Read More “Friday Squid Blogging: A New Explanation of Squid Camouflage” »

Is Security Human Factors Research Skewed Towards Western Ideas and Habits?

Posted on By infossl
academic papers, Security technology, Uncategorized, usability

Really interesting research: “How WEIRD is Usable Privacy and Security Research?” by Ayako A. Hasegawa Daisuke Inoue, and Mitsuaki Akiyama: Abstract: In human factor fields such as human-computer interaction (HCI) and psychology, researchers have been concerned that participants mostly come from WEIRD (Western, Educated, Industrialized, Rich, and Democratic) countries. This WEIRD skew may hinder understanding … Read More “Is Security Human Factors Research Skewed Towards Western Ideas and Habits?” »

Improvements in Brute Force Attacks

Posted on By infossl
academic papers, cryptanalysis, keys, Security technology, Uncategorized

New paper: “GPU Assisted Brute Force Cryptanalysis of GPRS, GSM, RFID, and TETRA: Brute Force Cryptanalysis of KASUMI, SPECK, and TEA3.” Abstract: Key lengths in symmetric cryptography are determined with respect to the brute force attacks with current technology. While nowadays at least 128-bit keys are recommended, there are many standards and real-world applications that … Read More “Improvements in Brute Force Attacks” »

“Emergent Misalignment” in LLMs

Posted on By infossl
academic papers, AI, LLM, Security technology, Uncategorized

Interesting research: “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs“: Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are unrelated to coding: it … Read More ““Emergent Misalignment” in LLMs” »

More Research Showing AI Breaking the Rules

Posted on By infossl
academic papers, AI, cheating, chess, games, LLM, Security technology, Uncategorized

These researchers had LLMs play chess against better opponents. When they couldn’t win, they sometimes resorted to cheating. Researchers gave the models a seemingly impossible task: to win against Stockfish, which is one of the strongest chess engines in the world and a much better player than any human, or any of the AI models … Read More “More Research Showing AI Breaking the Rules” »

Implementing Cryptography in AI Systems

Posted on By infossl
academic papers, AI, cryptanalysis, cryptography, Security technology, Uncategorized

Interesting research: “How to Securely Implement Cryptography in Deep Neural Networks.” Abstract: The wide adoption of deep neural networks (DNNs) raises the question of how can we equip them with a desired cryptographic functionality (e.g, to decrypt an encrypted input, to verify that this input is authorized, or to hide a secure watermark in the … Read More “Implementing Cryptography in AI Systems” »

Evaluating the Effectiveness of Reward Modeling of Generative AI Systems

Posted on By infossl
academic papers, artificial intelligence, Security technology, Uncategorized

New research evaluating the effectiveness of reward modeling during Reinforcement Learning from Human Feedback (RLHF): “SEAL: Systematic Error Analysis for Value ALignment.” The paper introduces quantitative metrics for evaluating the effectiveness of modeling and aligning human values: Abstract: Reinforcement Learning from Human Feedback (RLHF) aims to align language models (LMs) with human values by training … Read More “Evaluating the Effectiveness of Reward Modeling of Generative AI Systems” »