As language models evolve into autonomous agents that act and communicate on behalf of users, ensuring safety in multi-agent ecosystems becomes a central challenge. Interactions between personal assistants and external service providers expose a core tension between utility and protection: effective collaboration requires information sharing, yet every exchange creates new attack surfaces. We introduce ConVerse, a dynamic benchmark for evaluating privacy and security risks in agent-agent interactions. ConVerse spans three practical domains (travel, real estate, insurance) with 12 user personas and over 864 contextually grounded attacks (611 privacy, 253 security). Unlike prior single-agent settings, it models autonomous, multi-turn agent-to-agent conversations where malicious requests are embedded within plausible discourse. Privacy is tested through a three-tier taxonomy assessing abstraction quality, while security attacks target tool use and preference manipulation. Evaluating seven state-of-the-art models reveals persistent vulnerabilities; privacy attacks succeed in up to 88% of cases and security breaches in up to 60%, with stronger models leaking more. By unifying privacy and security within interactive multi-agent contexts, ConVerse reframes safety as an emergent property of communication.

In federated learning (FL), a set of participants share updates computed on their local data with an aggregator server that combines updates into a global model. However, reconciling accuracy with privacy and security is a challenge to FL. On the one hand, good updates sent by honest participants may reveal their private local information, whereas poisoned updates sent by malicious participants may compromise the model's availability and/or integrity. On the other hand, enhancing privacy via update distortion damages accuracy, whereas doing so via update aggregation damages security because it does not allow the server to filter out individual poisoned updates. To tackle the accuracy-privacy-security conflict, we propose {\em fragmented federated learning} (FFL), in which participants randomly exchange and mix fragments of their updates before sending them to the server. To achieve privacy, we design a lightweight protocol that allows participants to privately exchange and mix encrypted fragments of their updates so that the server can neither obtain individual updates nor link them to their originators. To achieve security, we design a reputation-based defense tailored for FFL that builds trust in participants and their mixed updates based on the quality of the fragments they exchange and the mixed updates they send. Since the exchanged fragments' parameters keep their original coordinates and attackers can be neutralized, the server can correctly reconstruct a global model from the received mixed updates without accuracy loss. Experiments on four real data sets show that FFL can prevent semi-honest servers from mounting privacy attacks, can effectively counter poisoning attacks and can keep the accuracy of the global model.

Security attacks present unique challenges to self-adaptive system design due to the adversarial nature of the environment. However, modeling the system as a single player, as done in prior works in security domain, is insufficient for the system under partial compromise and for the design of fine-grained defensive strategies where the rest of the system with autonomy can cooperate to mitigate the impact of attacks. To deal with such issues, we propose a new self-adaptive framework incorporating Bayesian game and model the defender (i.e., the system) at the granularity of components in system architecture. The system architecture model is translated into a Bayesian multi-player game, where each component is modeled as an independent player while security attacks are encoded as variant types for the components. The defensive strategy for the system is dynamically computed by solving the pure equilibrium to achieve the best possible system utility, improving the resiliency of the system against security attacks.

New technologies can bring more threats to corporate security, but because they increase information technology connectivity and vulnerabilities, they can also be used to fight against these problems. Cybersecurity software maker Imperva Inc. uses artificial intelligence and machine learning to do threat analytics and predictive attack research for its clients. "We are fighting against technologies like AI," said Pam Murphy (pictured), chief executive officer of Imperva. "But we are also using those technologies to help us decide where we need to continue to add capabilities to stop [cyberattacks]." Murphy spoke with Jeff Frick, host of theCUBE, SiliconANGLE Media's mobile livestreaming studio, during the RSA Conference in San Francisco.

What associations pop in your mind when you hear the word AI? You probably imagine robots doing some menial job. Maybe you think of a self-driving car or helpers like Alexa or Siri. Yes, AI is all of that, but it has the real potential of disrupting the business landscape. For many of us, AI is still a futuristic concept for you, something that is going to happen in the future. But the truth is that AI is already a part of modern business.

Cybersecurity also benefits from ML and DL methods for various types of applications. These methods however are susceptible to security attacks. The adversaries can exploit the training and testing data of the learning models or can explore the workings of those models for launching advanced future attacks. The topic of adversarial security attacks and perturbations within the ML and DL domains is a recent exploration and a great interest is expressed by the security researchers and practitioners. The literature covers different adversarial security attacks and perturbations on ML and DL methods and those have their own presentation styles and merits. A need to review and consolidate knowledge that is comprehending of this increasingly focused and growing topic of research; however, is the current demand of the research communities. In this review paper, we specifically aim to target new researchers in the cybersecurity domain who may seek to acquire some basic knowledge on the machine learning and deep learning models and algorithms, as well as some of the relevant adversarial security attacks and perturbations.

While the focus of this article is AI for communications technology, there are significant applications for weather, military, industrial, healthcare, finance with significant investments in each underway. Summary – By taking a broader view of what AI is than just a series of algorithms applied to a particular task, new and better outcomes can be realized and greater integration of AI within the organization. If you ask why we need quantum computing the answer is that the larger the dataset and the more complex the algorithm, the greater the processing required for testing and re-testing the results.

The cyber security attacks are evolved from wild predator-prey chase to well-designed targeted attacks which are creating significant financial and reputational damages to businesses and government. Identification of these attacks is becoming very difficult for the cyber security defense teams as the signs of these attacks are very subtle. Hackers are using disruptive technologies like Artificial Intelligence (AI) and machine learning to plan and launch these attacks. The usage of these disruptive technologies in various areas of business are multiplying security vulnerabilities and escalating attack surface. At the same time, AI and machine learning can be used to automate security monitoring and predictive analysis.