LIVE · cybersecurity feed
Live wire
vulnerability

Cisco's open-weight bug busters take on Google and OpenAI

Cisco has introduced two new open-weight small language models (SLMs), Antares-350M and Antares-1B, designed specifically for identifying known vulnerabilities in existing codebases. These models are now available on Hugging Face, with access granted to vetted users, including academic institutions, nonprofit organizations, and security teams from public and smaller organizations.

ZeroDay News ·

Source: The Register — Security

Cisco has introduced two new open-weight small language models (SLMs), Antares-350M and Antares-1B, designed specifically for identifying known vulnerabilities in existing codebases. These models are now available on Hugging Face, with access granted to vetted users, including academic institutions, nonprofit organizations, and security teams from public and smaller organizations.

The Antares models are part of Cisco's new Antares family of security SLMs, named after the red supergiant star. A key advantage of these models is their ability to run locally, ensuring that proprietary code remains within an organization's machines. This addresses privacy and compliance concerns associated with cloud-based large language models (LLMs) that send code to external servers for processing.

Cisco emphasizes that the Antares models are not chatbots but rather "investigators" or "search engines" specialized in vulnerability detection. This focused design allows them to efficiently locate specific security flaws, even within millions of lines of code. According to Cisco, the models were trained using a unique approach that enables them to employ multiple search strategies simultaneously.

The company claims that Antares-1B performs comparably to or better than several larger models in identifying security flaws. In Cisco's internal benchmark tests, Antares-1B reportedly outperforms Google’s Gemini 3 Pro and is on par with Z.ai's GLM-5.2. A future, unreleased model, Antares-3B, is said to surpass both GLM-5.2 and OpenAI’s GPT-5.5 in vulnerability detection.

Beyond performance, Cisco highlights the speed and cost-efficiency of its SLMs. The company states that Antares models can scan 500 code repositories in approximately 15 minutes, a task that frontier models might take five hours to complete. This efficiency translates to significantly lower operational costs, estimated at less than $1 per scan compared to $100-$150 for larger models.

While Antares-350M and Antares-1B are publicly available to vetted users, a larger 3-billion-parameter model in the Antares family, Antares-3B, will not be released to the public. Cisco intends to gate access to Antares-3B, ensuring its responsible distribution to specific communities that require it.

vulnerabilityai
ShareXLinkedInWhatsAppFacebook

More News

view all →
security

Canadian cybersecurity executive arrested in federal extortion case

A Canadian cybersecurity executive was arrested in Pennsylvania on Thursday, facing federal charges of conspiracy to commit extortion. Edward Dubrovsky, 54, a co-founder and former Chief Operating Officer of CYPFER, a firm specializing in ransomware negotiation, is charged with conspiring to threaten the confidentiality of information for extortion and conspiring to commit Hobbs Act extortion,…

breach

Criminal IP Introduces AITEM as the Next Evolution of Attack Surface Management

AI SPERA, the company behind the cyber threat intelligence platform Criminal IP, has announced AITEM (AI-Powered Threat Exposure Management), an expansion of its Attack Surface Management (ASM) offerings. AITEM aims to move beyond traditional asset discovery to provide a more comprehensive approach to understanding, prioritizing, and responding to security exposures. The platform is scheduled…

ai

AI Is Getting Really Good at Messing With Cybercriminals

Anti-cybercrime initiatives are increasingly deploying artificial intelligence to disrupt scammers by engaging them with lifelike bots, which the criminals mistake for genuine victims. This strategy aims to waste scammers' time and resources while gathering intelligence on their operations.

ransomware

FBI Arrests Ransomware Negotiation Firm Co-Founder in ShinyHunters Probe

The Federal Bureau of Investigation (FBI) has reportedly arrested Edward Dubrovsky, a co-founder of the ransomware negotiation firm Cypfer and currently associated with CyberSteward. The arrest is said to be part of the ongoing ShinyHunters investigation, specifically in connection with an incident involving FBI job applicant data.

ai

The Third-Party Agent Problem: Why Security Built for AI You Chose Misses the Agents You Didn't

A new report highlights a significant blind spot in enterprise security architectures concerning the proliferation of third-party AI agents. The forthcoming 2026 State of Agent Security Report indicates that current security models, often designed to protect AI systems directly chosen and deployed by an organization, frequently fail to account for AI capabilities embedded within third-party…

security

Insider Cyber Extortion Plot Against Industrial Firm Lands Engineer in Prison

A former core infrastructure engineer has been sentenced to prison for an attempted cyber extortion plot against an industrial firm. The engineer reportedly deleted administrative accounts and reset hundreds of user passwords, subsequently demanding a ransom of 20 Bitcoin to prevent further disruption to the company's servers.