Yair Meidan

Yair Meidan, Dan Avraham, Hanan Libhaber et al.

Although home IoT (Internet of Things) devices are typically plain and task oriented, the context of their daily use may affect their traffic patterns. For this reason, anomaly-based intrusion detection systems tend to suffer from a high false positive rate (FPR). To overcome this, we propose a two-step collaborative anomaly detection method which first uses an autoencoder to differentiate frequent (`benign') and infrequent (possibly `malicious') traffic flows. Clustering is then used to analyze only the infrequent flows and classify them as either known ('rare yet benign') or unknown (`malicious'). Our method is collaborative, in that (1) normal behaviors are characterized more robustly, as they take into account a variety of user interactions and network topologies, and (2) several features are computed based on a pool of identical devices rather than just the inspected device. We evaluated our method empirically, using 21 days of real-world traffic data that emanated from eight identical IoT devices deployed on various networks, one of which was located in our controlled lab where we implemented two popular IoT-related cyber-attacks. Our collaborative anomaly detection method achieved a macro-average area under the precision-recall curve of 0.841, an F1 score of 0.929, and an FPR of only 0.014. These promising results were obtained by using labeled traffic data from our lab as the test set, while training the models on the traffic of devices deployed outside the lab, and thus demonstrate a high level of generalizability. In addition to its high generalizability and promising performance, our proposed method also offers benefits such as privacy preservation, resource savings, and model poisoning mitigation. On top of that, as a contribution to the scientific community, our novel dataset is available online.

Yair Meidan, Omri Haller, Yulia Moshan et al.

Recent advances in large language models and agentic frameworks have enabled virtual customer assistants (VCAs) for complex support. We present SecMate, a multi-agent VCA for cybersecurity troubleshooting that integrates device, user, and service specificity from conversational and device-level signals. Device specificity is provided by a lightweight local diagnostic utility, while user specificity relies on implicit proficiency inference and profile-aware troubleshooting. Service specificity is achieved through a proactive, context-aware recommender. We evaluate SecMate in a controlled study with 144 participants and 711 conversations. Device-level evidence increased correct resolutions from about 50% to over 90% relative to an LLM-only baseline, while step-by-step guidance improved pleasantness and reduced user burden. The recommender achieved high relevance (MRR@1=0.75), and participants showed strong willingness to substitute human IT support at costs well below human benchmarks. We release the full code base and a richly annotated dataset to support reproducible research on adaptive VCAs.

Shahaf David, Yair Meidan, Ido Hersko et al.

Despite significant advancements in conversational AI, large language model (LLM)-powered chatbots often struggle with personalizing their responses according to individual user characteristics, such as technical expertise, learning style, and communication preferences. This lack of personalization is particularly problematic in specialized knowledge-intense domains like IT/cybersecurity (ITSec), where user knowledge levels vary widely. Existing approaches for chatbot personalization primarily rely on static user categories or explicit self-reported information, limiting their adaptability to an evolving perception of the user's proficiency, obtained in the course of ongoing interactions. In this paper, we propose ProfiLLM, a novel framework for implicit and dynamic user profiling through chatbot interactions. This framework consists of a taxonomy that can be adapted for use in diverse domains and an LLM-based method for user profiling in terms of the taxonomy. To demonstrate ProfiLLM's effectiveness, we apply it in the ITSec domain where troubleshooting interactions are used to infer chatbot users' technical proficiency. Specifically, we developed ProfiLLM[ITSec], an ITSec-adapted variant of ProfiLLM, and evaluated its performance on 1,760 human-like chatbot conversations from 263 synthetic users. Results show that ProfiLLM[ITSec] rapidly and accurately infers ITSec profiles, reducing the gap between actual and predicted scores by up to 55--65\% after a single prompt, followed by minor fluctuations and further refinement. In addition to evaluating our new implicit and dynamic profiling framework, we also propose an LLM-based persona simulation methodology, a structured taxonomy for ITSec proficiency, our codebase, and a dataset of chatbot interactions to support future research.

Omri Haller, Yair Meidan, Dudu Mimran et al.

Following recent advancements in large language models (LLMs), LLM-based chatbots have transformed customer support by automating interactions and providing consistent, scalable service. While LLM-based conversational recommender systems (CRSs) have attracted attention for their ability to enhance the quality of recommendations, limited research has addressed the implicit integration of recommendations within customer support interactions. In this work, we introduce ImpReSS, an implicit recommender system designed for customer support conversations. ImpReSS operates alongside existing support chatbots, where users report issues and chatbots provide solutions. Based on a customer support conversation, ImpReSS identifies opportunities to recommend relevant solution product categories (SPCs) that help resolve the issue or prevent its recurrence -- thereby also supporting business growth. Unlike traditional CRSs, ImpReSS functions entirely implicitly and does not rely on any assumption of a user's purchasing intent. Our empirical evaluation of ImpReSS's ability to recommend relevant SPCs that can help address issues raised in support conversations shows promising results, including an MRR@1 (and recall@3) of 0.72 (0.89) for general problem solving, 0.82 (0.83) for information security support, and 0.85 (0.67) for cybersecurity troubleshooting. To support future research, our data and code will be shared upon request.

Yair Meidan, Vinay Sachidananda, Yuval Elovici et al.

Today, telecommunication service providers (telcos) are exposed to cyber-attacks executed by compromised IoT devices connected to their customers' networks. Such attacks might have severe effects not only on the target of attacks but also on the telcos themselves. To mitigate those risks we propose a machine learning based method that can detect devices of specific vulnerable IoT models connected behind a domestic NAT, thereby identifying home networks that pose a risk to the telco's infrastructure and availability of services. As part of the effort to preserve the domestic customers' privacy, our method relies on NetFlow data solely, refraining from inspecting the payload. To promote future research in this domain we share our novel dataset, collected in our lab from numerous and various commercial IoT devices.

Ben Nassi, Moshe Sror, Ido Lavi et al.

The current generation of IoT devices is being used by clients and consumers to regulate resources (such as water and electricity) obtained from critical infrastructure (such as urban water services and smart grids), creating a new attack vector against critical infrastructure. In this research we show that smart irrigation systems, a new type of green technology and IoT device aimed at saving water and money, can be used by attackers as a means of attacking urban water services. We present a distributed attack model that can be used by an attacker to attack urban water services using a botnet of commercial smart irrigation systems. Then, we show how a bot running on a compromised device in a LAN can:(1) detect a connected commercial smart irrigation system (RainMachine, BlueSpray, and GreenIQ) within 15 minutes by analyzing LAN's behavior using a dedicated classification model, and (2) launch watering via a commercial smart irrigation system according to an attacker's wishes using spoofing and replay attacks. In addition, we model the damage that can be caused by performing such an attack and show that a standard water tower can be emptied in an hour using a botnet of 1,355 sprinklers and a flood water reservoir can be emptied overnight using a botnet of 23,866 sprinklers. Finally, we discuss countermeasure methods and hypothesize whether the next generation of plumbers will use Kali Linux instead of a monkey wrench.

Yair Meidan, Michael Bohadana, Asaf Shabtai et al.

Security experts have demonstrated numerous risks imposed by Internet of Things (IoT) devices on organizations. Due to the widespread adoption of such devices, their diversity, standardization obstacles, and inherent mobility, organizations require an intelligent mechanism capable of automatically detecting suspicious IoT devices connected to their networks. In particular, devices not included in a white list of trustworthy IoT device types (allowed to be used within the organizational premises) should be detected. In this research, Random Forest, a supervised machine learning algorithm, was applied to features extracted from network traffic data with the aim of accurately identifying IoT device types from the white list. To train and evaluate multi-class classifiers, we collected and manually labeled network traffic data from 17 distinct IoT devices, representing nine types of IoT devices. Based on the classification of 20 consecutive sessions and the use of majority rule, IoT device types that are not on the white list were correctly detected as unknown in 96% of test cases (on average), and white listed device types were correctly classified by their actual types in 99% of cases. Some IoT device types were identified quicker than others (e.g., sockets and thermostats were successfully detected within five TCP sessions of connecting to the network). Perfect detection of unauthorized IoT device types was achieved upon analyzing 110 consecutive sessions; perfect classification of white listed types required 346 consecutive sessions, 110 of which resulted in 99.49% accuracy. Further experiments demonstrated the successful applicability of classifiers trained in one location and tested on another. In addition, a discussion is provided regarding the resilience of our machine learning-based IoT white listing method to adversarial attacks.