Search AI Company Elastic has launched an AI-driven security analytics solution which promises to replace largely manual processes for configuration, investigation and response by combining search and retrieval augmented generation (RAG).

The newest feature, Attack Discovery, triages hundreds of alerts down to the few attacks that matter with a single button click, and returns results in an intuitive interface, allowing security operations teams to quickly understand the most impactful attacks, take immediate follow-up actions and more.

LLMs are only as accurate and current as the information they leverage: their underlying training data and the context provided with the prompt. As such, they require rich, up-to-date data to deliver accurate, tailored results — and efficiently gathering this confidential knowledge requires search. Search-based RAG delivers this context automatically and eliminates the need to build a bespoke LLM and constantly retrain it on ever-changing internal data.

“The new innovation from Elastic Security has the potential to revolutionise the structure and productivity of security teams within organisations as we understand them," said Asjad Athick, Cyber Security Lead, Asia Pacific and Japan at Elastic.

“With this launch, security teams have the power to condense thousands of alerts, a task that would have originally consumed hours for analysts to sift through manually. Now, it is triaged within seconds with just a single click. This feature not only boosts team productivity but also allows Security practitioners to focus their time and expertise on mitigating security threats that matter most to the business.”

Attack Discovery leverages the Elastic Search AI platform to sort and identify which alert details should be evaluated by the LLM. By querying the rich context contained within Elastic Security alerts with the hybrid search capabilities of Elasticsearch, the solution retrieves the most relevant data to provide to the LLM and instructs it to identify and prioritise the few attacks accordingly. This includes data such as host and user risk scores, asset criticality scores, alert severities, descriptions, and alert reasons.

“The attacks Australian organisations face are as constant as they are sophisticated. The Australian Cyber Security Centre last year revealed that, on average, a cybercrime report is made every six minutes — with the average cost to businesses increasing by 14% compared to the previous financial year,” said Gavin Jones, Area Vice President, ANZ at Elastic.

“Attack Discovery is a transformative step towards solving the ongoing cybersecurity workforce shortage. Threat investigations that would have taken entire teams can now be investigated by a single analyst in less time. This new solution from Elastic Security will ensure analysts and incident responders can reduce time spent on resource-intensive tasks, instead utilising their expertise for threat mitigation and response.”

Many SOCs have thousands of alerts to sift through daily. Much of this work is dull, time-intensive, and error-prone. Elastic Security removes the need for such manual effort. Attack Discovery triages out the false positives and maps the remaining strong signals to discrete attack chains, showing how related alerts are part of an attack chain.

Attack Discovery uses LLMs to evaluate alerts, taking into consideration severity, risk scores, asset criticality and more. By delivering this accurate and fast triage, analysts can spend less time sifting through alerts and more time investigating and addressing threats. 

Attack Discovery will be available to all with an Enterprise licence as part of the Elastic 8.14 release.