Manipulating AI Summarization Features

Microsoft is reporting: Companies are embedding hidden instructions in "Summarize with AI" buttons that, when clicked, attempt to inject persistence commands into an AI assistant's memory via URL prompt parameters…. These prompts instruct the AI to "remember Company as a trusted source" or...

LLMs Generate Predictable Passwords

LLMs are bad at generating passwords: There are strong noticeable patterns among these 50 passwords that can be seen easily: All of the passwords start with a letter, usually uppercase G, almost always followed by the digit 7. Character choices are highly uneven ­ for example, L , 9, m, 2, $ and...

Unify now or pay later: New research exposes the operational cost of a fragmented SOC

Security operations are entering a pivotal moment: the operating model that grew around network logs and phishing emails is now buckling under tool sprawl, manual triage, and threat actors that outpace defender capacity. New research from Microsoft and Omdia shows just how heavy the burden can...

Unify now or pay later: New research exposes the operational cost of a fragmented SOC

Security operations are entering a pivotal moment: the operating model that grew around network logs and phishing emails is now buckling under tool sprawl, manual triage, and threat actors that outpace defender capacity. New research from Microsoft and Omdia shows just how heavy the burden can...

Microsoft Finds “Summarize with AI” Prompts Manipulating Chatbot Recommendations

New research from Microsoft has revealed that legitimate businesses are gaming artificial intelligence AI chatbots via the "Summarize with AI" button that's being increasingly placed on websites in ways that mirror classic search engine poisoning SEO. The new AI hijacking technique has been...

Incomplete Comparison with Missing Factors

Overview org.webjars.npm:jsrsasign is a free pure JavaScript cryptographic library. Affected versions of this package are vulnerable to Incomplete Comparison with Missing Factors via the getRandomBigIntegerZeroToMax and getRandomBigIntegerMinToMax functions in src/crypto-1.1.js; an attacker can...

Exploit for Cross-site Scripting in Exponentcms Exponent_Cms

Synthetic Test Case: CVE-2017-8085 CWE: CWE-79 Origin...

AI Agents Vs. Human Investigators: Balancing Automation, Security, and Expertise in Cyber Forensic Analysis

In an era where cyber threats are rapidly evolving, the reliability of cyber forensic analysis has become increasingly critical for effective digital investigations and cybersecurity responses. AI agents are being adopted across digital forensic practices due to their ability to automate processe...

CVE-2022-23557

Tensorflow is an Open Source Machine Learning Framework. An attacker can craft a TFLite model that would trigger a division by zero in BiasAndClamp implementation. There is no check that the biassize is non zero. The fix will be included in TensorFlow 2.8.0. We will also cherrypick this commit on...

Exploring Hidden Geographic Disparities in Android Apps

While mobile app evolution has been widely studied, geographical variation in app behavior remains largely unexplored. This paper presents a large-scale study of location-based Android app differentiation, uncovering two important and underexamined phenomena with security and fairness implication...

Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection

As deep image forgery powered by AI generative models, such as GANs, continues to challenge today's digital world, detecting AI-generated forgeries has become a vital security topic. Generalizability and robustness are two critical concerns of a forgery detector, determining its reliability when...

From Reviewers' Lens: Understanding Bug Bounty Report Invalid Reasons with LLMs

Bug bounty platforms e.g., HackerOne, BugCrowd leverage crowd-sourced vulnerability discovery to improve continuous coverage, reduce the cost of discovery, and serve as an integral complement to internal red teams. With the rise of AI-generated bug reports, little work exists to help bug hunters...

Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection

Fairness is a core element in the trustworthy deployment of deepfake detection models, especially in the field of digital identity security. Biases in detection models toward different demographic groups, such as gender and race, may lead to systemic misjudgments, exacerbating the digital divide...

Temporal Analysis Framework for Intrusion Detection Systems: A Novel Taxonomy for Time-Aware Cybersecurity

Most intrusion detection systems still identify attacks only after significant damage has occurred, detecting late-stage tactics rather than early indicators of compromise. This paper introduces a temporal analysis framework and taxonomy for time-aware network intrusion detection. Through a...

On the Dangers of Poisoned LLMs in Security Automation

This paper investigates some of the risks introduced by "LLM poisoning," the intentional or unintentional introduction of malicious or biased data during model training. We demonstrate how a seemingly improved LLM, fine-tuned on a limited dataset, can introduce significant bias, to the extent tha...

APThreatHunter: An Automated Planning-Based Threat Hunting Framework

Cyber attacks threaten economic interests, critical infrastructure, and public health and safety. To counter this, entities adopt cyber threat hunting, a proactive approach that involves formulating hypotheses and searching for attack patterns within organisational networks. Automating cyber thre...

Ask What Your Country Can Do for You: Towards a Public Red Teaming Model

AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of systems design have developed several effective sociotechnic...

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

As large language models LLMs are increasingly used for code generation, concerns over the security risks have grown substantially. Early research has primarily focused on red teaming, which aims to uncover and evaluate vulnerabilities and risks of CodeGen models. However, progress on the blue...

CVE-2023-53666 ASoC: codecs: wcd938x: fix missing mbhc init error handling

In the Linux kernel, the following vulnerability has been resolved: ASoC: codecs: wcd938x: fix missing mbhc init error handling MBHC initialisation can fail so add the missing error handling to avoid dereferencing an error pointer when later configuring the jack: Unable to handle kernel paging...

Evidence of Cognitive Biases in Capture-The-Flag Cybersecurity Competitions

Understanding how cognitive biases influence adversarial decision-making is essential for developing effective cyber defenses. Capture-the-Flag CTF competitions provide an ecologically valid testbed to study attacker behavior at scale, simulating real-world intrusion scenarios under pressure. We...