Evaluating the Critical Risks of Amazon'S Nova Premier under the Frontier Model Safety Framework

Nova Premier is Amazon's most capable multimodal foundation model and teacher for model distillation. It processes text, images, and video with a one-million-token context window, enabling analysis of large codebases, 400-page documents, and 90-minute videos in a single prompt. We present the fir...

Design Patterns for Securing LLM Agents against Prompt Injections

As AI agents powered by Large Language Models LLMs become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on...

ATAG: AI-Agent Application Threat Assessment with Attack Graphs

Evaluating the security of multi-agent systems MASs powered by large language models LLMs is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack graph AG methods often lack the specific capabilities to model...

Server-Side Template Injection Vulnerabilities and Exploitation Techniques

Research article called Server-Side Template Injection SSTI Vulnerabilities and Exploitation Techniques. The paper provides a structured methodology for detecting and exploiting SSTI vulnerabilities across multiple template engines, along with real-world case studies and mitigation strategies...

On the Security Risks of ML-Based Malware Detection Systems: a Survey

Malware presents a persistent threat to user privacy and data integrity. To combat this, machine learning-based ML-based malware detection MD systems have been developed. However, these systems have increasingly been attacked in recent years, undermining their effectiveness in practice. While the...

Side Channel Analysis in Homomorphic Encryption

Homomorphic encryption provides many opportunities for privacy-aware processing, including with methods related to machine learning. Many of our existing cryptographic methods have been shown in the past to be susceptible to side channel attacks. With these, the implementation of the cryptographi...

Causality for Cyber-Physical Systems

We present a formal theory for analysing causality in cyber-physical systems. To this end, we extend the theory of actual causality by Halpern and Pearl to cope with the continuous nature of cyber-physical systems. Based on our theory, we develop an analysis technique that is used to uncover the...

Towards a Standardized Methodology and Dataset for Evaluating LLM-Based Digital Forensic Timeline Analysis

Large language models LLMs have seen widespread adoption in many domains including digital forensics. While prior research has largely centered on case studies and examples demonstrating how LLMs can assist forensic investigations, deeper explorations remain limited, i.e., a standardized approach...

Breaking the Flow and the Bank: Stealthy Cyberattacks on Water Network Hydraulics

As water distribution networks WDNs become increasingly connected with digital infrastructures, they face greater exposure to cyberattacks that threaten their operational integrity. Stealthy False Data Injection Attacks SFDIAs are particularly concerning, as they manipulate sensor data to...

Rogue AI: What the Security Community is Missing

This is the fourth blog post in an ongoing series on Rogue AI. Keep following for more technical guidance, case studies, and insights...

Identifying Rogue AI

This is the third blog in an ongoing series on Rogue AI. Keep following for more technical guidance, case studies, and insights...

Chinese-Speaking Hacker Group Targets Human Rights Studies in Middle East

Unnamed government entities in the Middle East and Malaysia are the target of a persistent cyber campaign orchestrated by a threat actor known as Tropic Trooper since June 2023. "Sighting this group's Tactics, Techniques, and Procedures in critical governmental entities in the Middle East,...

How AI Goes Rogue

This is the second blog in an ongoing series on Rogue AI. Keep following for more technical guidance, case studies, and insights...

Rogue AI is the Future of Cyber Threats

This is the first blog in a series on Rogue AI. Later articles will include technical guidance, case studies and more...

On the Voynich Manuscript

Really interesting article on the ancient-manuscript scholars who are applying their techniques to the Voynich Manuscript. No one has been able to understand the writing yet, but there are some new understandings: Davis presented her findings at the medieval-studies conference and published them ...

This Week in Spring - August 13th, 2024

Hi, Spring fans! Welcome to another installment of This Week in Spring! It's Tuesday and work is well underway to prepare for the huge SpringOne event in Las Vegas in just a few short week's time! I'm elated! So, let's get this roundup on the road so I can get back to the preparation frenzy...

Microsoft Technical Case Studies athena-dashboard Uncontrolled Search Path Element Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of Microsoft Technical Case Studies. Authentication is not required to exploit this vulnerability. The specific flaw exists within the installation of Technical Case Studies. When installed from the...

asia-studies.org Cross Site Scripting vulnerability OBB-3669584

Following the coordinated and responsible vulnerability disclosure guidelines of the ISO 29147 standard, Open Bug Bounty has: a. verified the vulnerability and confirmed its existence; b. notified the website operator about its existence. Technical details of the vulnerability are currently hidde...

Examining Ransomware Payments From a Data-Science Lens

In this entry, we discuss case studies that demonstrated how data-science techniques were applied in our investigation of ransomware groups' ransom transactions, as detailed in our joint research with Waratah Analytics, “What Decision-Makers Need to Know About Ransomware Risk.”...

My SpringOne 2022

It has taken me an embarrassingly long time to appreciate and understand that the devil is in the details regarding software development. Writing happy-path business logic isnt the hard part! Its the failure cases, observability, resilience, and process. Its security and other so-called...