Anomaly detection in cybersecurity has lengthy promised the flexibility to establish threats by highlighting deviations from anticipated conduct. In relation to figuring out malicious instructions, nevertheless, its sensible utility usually ends in excessive charges of false positives – making it costly and inefficient. However with current improvements in AI, is there a unique approach that now we have but to discover?
In our speak at Black Hat USA 2025, we introduced our analysis into creating a pipeline that doesn’t rely on anomaly detection as a degree of failure. By combining anomaly detection with giant language fashions (LLMs), we are able to confidently establish important information that can be utilized to reinforce a devoted command-line classifier.
Utilizing anomaly detection to feed a distinct course of avoids the doubtless catastrophic false-positive charges of an unsupervised technique. As an alternative, we create enhancements in a supervised mannequin focused in direction of classification.
Unexpectedly, the success of this technique didn’t rely on anomaly detection finding malicious command traces. As an alternative, anomaly detection, when paired with LLM-based labeling, yields a remarkably various set of benign command traces. Leveraging these benign information when coaching command-line classifiers considerably reduces false-positive charges. Moreover, it permits us to make use of plentiful current information with out the needles in a haystack which can be malicious command traces in manufacturing information.
On this article, we’ll discover the methodology of our experiment, highlighting how various benign information recognized via anomaly detection broadens the classifier’s understanding and contributes to making a extra resilient detection system.
By shifting focus from solely aiming to seek out malicious anomalies to harnessing benign range, we provide a possible paradigm shift in command-line classification methods.
Cybersecurity practitioners usually should strike a steadiness between expensive labeled datasets and noisy unsupervised detections. Conventional benign labeling focuses on ceaselessly noticed, low-complexity benign behaviors, as a result of that is simple to realize at scale, inadvertently excluding uncommon and complex benign instructions. This hole prompts classifiers to misclassify refined benign instructions as malicious, driving false optimistic charges greater.
Latest developments in LLMs have enabled extremely exact AI-based labeling at scale. We examined this speculation by labelling anomalies detected in actual manufacturing telemetry (over 50 million day by day instructions), attaining near-perfect precision on benign anomalies. Utilizing anomaly detection explicitly to boost the protection of benign information, our goal was to vary the function of anomaly detection – shifting from erratically figuring out malicious conduct to reliably highlighting benign range. This strategy is essentially new, as anomaly detection historically prioritizes malicious discoveries fairly than enhancing benign label range.
Utilizing anomaly detection paired with automated, dependable benign labeling from superior LLMs, particularly OpenAI’s o3-mini mannequin, we augmented supervised classifiers and considerably enhanced their efficiency.
Information assortment and featurization
We in contrast two distinct implementations of knowledge assortment and featurization over the month of January 2025, making use of every implementation day by day to judge efficiency throughout a consultant timeline.
Full-scale implementation (all out there telemetry)
The primary technique operated on full day by day Sophos telemetry, which included about 50 million distinctive command traces per day. This technique required scaling infrastructure utilizing Apache Spark clusters and automatic scaling by way of AWS SageMaker.
The options for the full-scale strategy have been based mostly totally on domain-specific guide engineering. We calculated a number of descriptive command-line options:
Entropy-based options measured command complexity and randomness
Character-level options encoded the presence of particular characters and particular tokens
Token-level options captured the frequency and significance of tokens throughout command-line distributions
Behavioral checks particularly focused suspicious patterns generally correlated with malicious intent, resembling obfuscation methods, information switch instructions, and reminiscence or credential-dumping operations.
Decreased-scale embeddings implementation (sampled subset)
Our second technique addressed scalability considerations through the use of day by day sampled subsets with 4 million distinctive command traces per day. Decreasing the computational load allowed for the analysis of efficiency trade-offs and useful resource efficiencies of a inexpensive strategy.
Notably, function embeddings and anomaly processing for this strategy might feasibly be executed on cheap Amazon SageMaker GPU cases and EC2 CPU cases – considerably reducing operational prices.
As an alternative of function engineering, the sampled technique used semantic embeddings generated from a pre-trained transformer embedding mannequin particularly designed for programming purposes: Jina Embeddings V2. This mannequin is explicitly pre-trained on command traces, scripting languages, and code repositories. Embeddings characterize instructions in a semantically significant, high-dimensional vector area, eliminating guide function engineering burdens and inherently capturing advanced command relationships.
Though embeddings from transformer-based fashions will be computationally intensive, the smaller information dimension of this strategy made their calculation manageable.
Using two distinct methodologies allowed us to evaluate whether or not we might acquire computational reductions with out appreciable lack of detection efficiency — a beneficial perception towards manufacturing deployment.
Anomaly detection methods
Following featurization, we detected anomalies with three unsupervised anomaly detection algorithms, every chosen resulting from distinct modeling traits. The isolation forest identifies sparse random partitions; a modified k-means makes use of centroid distance to seek out atypical factors that don’t observe widespread developments within the information; and principal element evaluation (PCA) locates information with giant reconstruction errors within the projected subspace.
Deduplication of anomalies and LLM labeling
With preliminary anomaly discovery accomplished, we addressed a sensible difficulty: anomaly duplication. Many anomalous instructions solely differed minimally from one another, resembling a small parameter change or a substitution of variable names. To keep away from redundancies and inadvertently up-weighting sure sorts of instructions, we established a deduplication step
We computed command-line embeddings utilizing the transformer mannequin (Jina Embeddings V2), then measured the similarity of anomaly candidates with cosine similarity comparisons. Cosine similarity gives a sturdy and environment friendly vector-based measure of semantic similarity between embedded representations, making certain that downstream labelling evaluation targeted on considerably novel anomalies.
Subsequently, anomalies have been categorized utilizing automated LLM-based labeling. Our technique used OpenAI’s o3-mini reasoning LLM, particularly chosen for its efficient contextual understanding of cybersecurity-related textual information, owing to its general-purpose fine-tuning on varied reasoning duties.
This mannequin robotically assigned every anomaly a transparent benign or malicious label, drastically decreasing expensive human analyst interventions.
The validation of LLM labeling demonstrated an exceptionally excessive precision for benign labels (close to 100%), confirmed by subsequent skilled analyst guide scoring throughout a full week of anomaly information. This excessive precision supported direct integration of labeled benign anomalies into subsequent phases for classifier coaching with excessive belief and minimal human validation.
This rigorously structured methodological pipeline — from complete information assortment to specific labeling — yielded various benign-labeled command datasets and considerably lowered false-positive charges when applied in supervised classification fashions.
The total-scale and reduced-scale implementations resulted in two separate distributions as seen in Figures 1 and a pair of respectively. To reveal the generalizability of our technique, we augmented two separate baseline coaching datasets: a regex baseline (RB) and an aggregated baseline (AB). The regex baseline sourced labels from static, regex-based guidelines and was meant to characterize one of many easiest attainable labeling pipelines. The aggregated baseline sourced labels from regex-based guidelines, sandbox information, buyer case investigations, and buyer telemetry. This represents a extra mature and complicated labeling pipeline.
Determine 1: Cumulative distribution of command traces gathered per day over the check month utilizing the full-scale technique. The graph reveals all command traces, deduplication by distinctive command line, and near-deduplication by cosine similarity of command line embeddings
Determine 2: Cumulative distribution of command traces gathered per day over the check month utilizing the reduced-scale technique. The lowered scale plateaus slower as a result of the sampled information is probably going discovering extra native optima
Coaching set
Incident check AUC
Time cut up check AUC
Aggregated Baseline (AB)
0.6138
0.9979
AB + Full-scale
0.8935
0.9990
AB + Decreased-scale Mixed
0.8063
0.9988
Regex Baseline (RB)
0.7072
0.9988
RB + Full-scale
0.7689
0.9990
RB + Decreased-scale Mixed
0.7077
0.9995
Desk 1: Space underneath the curve for the aggregated baseline and regex baseline fashions educated with extra anomaly-derived benign information. The aggregated baseline coaching set consists of buyer and sandbox information. The regex baseline coaching set consists of regex-derived information
As seen in Desk 1, we evaluated our educated fashions on each a time cut up check set and an expert-labeled benchmark derived from incident investigations and an energetic studying framework. The time cut up check set spans three weeks instantly succeeding the coaching interval. The expert-labeled benchmark intently resembles the manufacturing distribution of beforehand deployed fashions.
By integrating anomaly-derived benign information, we improved the realm underneath the curve (AUC) on the expert-labeled benchmark of the aggregated and regex baseline fashions by 27.97 factors and 6.17 factors respectively.
As an alternative of ineffective direct malicious classification, we reveal anomaly detection’s distinctive utility in enriching benign information protection within the lengthy tail – a paradigm shift that enhances classifier accuracy and minimizes false-positive charges.
Trendy LLMs have enabled automated pipelines for benign information labelling – one thing not attainable till not too long ago. Our pipeline was seamlessly built-in into an current manufacturing pipeline, highlighting its generic and adaptable nature.