Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis

Large Language Models LLMs are increasingly being used as security engineering tools to summarize and explain malware behavior to analysts. A common assumption is that Retrieval-Augmented Generation RAG improves explanation quality by injecting external security knowledge. In this work, we...

‘Get Down! Get Down! They’re Gonna See Us!’: Six Months of Hiding From ICE

A family in Chicago has been terrified to leave their apartment. Agents could be anywhere...

Now You Hear Me: Audio Narrative Attacks against Large Audio-Language Models

Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of vulnerabilities that remain largely uncharacterized. We exami...

MAL-2025-91804 Malicious code in vida-kue41-riris (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 0d5cad985c0f5a15044fe14dbb3ffa136d8bb3051bf76ed31a8cd29cbafd40ac This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models

Large language models LLMs remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker mode...

AutoBnB-RAG: Enhancing Multi-Agent Incident Response with Retrieval-Augmented Generation

Incident response IR requires fast, coordinated, and well-informed decision-making to contain and mitigate cyber threats. While large language models LLMs have shown promise as autonomous agents in simulated IR settings, their reasoning is often limited by a lack of access to external knowledge. ...

Threat Exposure as a Narrative: If Attackers Tell a Story, Why Don’t We?

Running short on time but still want to stay in the know? Well, we’ve got you covered! We’ve condensed all the key takeaways into a handy audio summary. Our AI-driven podcasts are fit for on the go. Security teams are losing the communication battle to cybercriminals who intuitively understand...

Threat Exposure as a Narrative: If Attackers Tell a Story, Why Don’t We?

Running short on time but still want to stay in the know? Well, we’ve got you covered! We’ve condensed all the key takeaways into a handy audio summary. Our AI-driven podcasts are fit for on the go. Security teams are losing the communication battle to cybercriminals who intuitively understand...

Chain-Of-Lure: a Synthetic Narrative-Driven Approach to Compromise Large Language Models

In the era of rapid generative AI development, interactions between humans and large language models face significant misusing risks. Previous research has primarily focused on black-box scenarios using human-guided prompts and white-box scenarios leveraging gradient-based LLM generation methods,...

CVE-2025-2715

A vulnerability classified as problematic has been found in timschofield webERP up to 5.0.0.rc+13. This affects an unknown part of the file ConfirmDispatchInvoice.php of the component Confirm Dispatch and Invoice Page. The manipulation of the argument Narrative leads to cross site scripting. It i...

PT-2025-12681

Name of the Vulnerable Software and Affected Versions timschofield webERP versions up to 5.0.0.rc+13 Description A problematic vulnerability has been found in timschofield webERP, affecting an unknown part of the file ConfirmDispatch Invoice.php of the component Confirm Dispatch and Invoice Page...

CVE-2025-2715: Improper Neutralization of Input During Web Page Generation

A vulnerability classified as problematic has been found in timschofield webERP up to 5.0.0.rc+13. This affects an unknown part of the file ConfirmDispatchInvoice.php of the component Confirm Dispatch and Invoice Page. The manipulation of the argument Narrative leads to cross site scripting. It i...

Story About Medical Device Security

Ben Rothke relates a story about me working with a medical device firm back when I was with BT. I don't remember the story at all, or who the company was. But it sounds about right...

The Real Story of “The Order”

The new film about an FBI agent chasing a white supremacist terror cell is based on a true story—and one that connects the headlines of 40 years ago to those of today...

Die Hard 2. Or how not to hack airplanes

How could I criticise possibly the best action movie series of all time? Well, it’s to help dispel myths about hacking planes. TV shows and films help set a narrative that is hard to shift around aviation cyber, giving the travelling public a misleading view of their security when flying. So let’...

Part I: Implementing Effective Cyber Security Metrics That Reduce Risk Realistically

As a CISO or business leader, some burning questions that often come to your mind are: How vulnerable is our cybersecurity posture? Are we better protected than we were three months or a year ago? Have our investments improved the cybersecurity posture and yielded any tangible benefits? Are my...

Microsoft reveals hackers viewed its source code

By Deeba Ahmed Microsoft confirmed that viewing source code doesn’t elevate the risk. Here's what happened and what Mircosoft said about the attack. This is a post from HackRead.com Read the original post: Microsoft reveals hackers viewed its source code...

RSAC 2020 Keynote: Changing the World's False Perception of Cybersecurity

SAN FRANCISCO – Today, cybersecurity is portrayed in the media and by businesses as an ongoing complex conflict between defenders and cybercriminals, with heightened noise around hyper-technical proof-of-concept attacks, or nation state threats. But, the reality is starkly different, said Rohit...

Lies and More Lies

Following the release of the Spectre and Meltdown CPU attacks, the security community wondered if other researchers would find related speculative attack problems. When the following appeared, we were concerned: "Skyfall and Solace More vulnerabilities in modern computers. Following the recent...

SteelCon: Mahkra ni Orroz

I recently gave a talk at Sheffield's SteelCon, a huge security event spread over a few days with no end of interesting activities taking place. My presentation, called Makhra ni Orroz, is a good 45 minutes of non stop talking and pictures and things. It's also a bit different in terms of what I...