Cutting-edge tech

Healthcare organizations have established specialized technical infrastructures that drive innovations in their products, research capabilities, and therapeutic technologies.

AstraZeneca has built AI-powered knowledge graphs that integrate complex biological relationships across genes, proteins, diseases, and drugs. This specialized infrastructure enables the identification of disease mechanisms and drug targets that would remain hidden using conventional research methods. Their use of language models like ChatGPT and ClinicalBERT to analyze scientific literature and clinical data enables rapid repurposing of existing medicines. The company’s MILTON AI tool, announced in September 2024, represents a significant technological advancement, predicting over 1,000 diseases before diagnosis to enhance early intervention and personalized treatments.

One of Medtronic’s most significant AI advancements is the GI Genius™ module, an AI-assisted colonoscopy tool that uses NVIDIA’s Holoscan and IGX technologies. This platform supports multiple AI algorithms, allowing third-party developers to create and deploy applications that enhance diagnostic accuracy in gastroenterology procedures. Medtronic’s Live Stream technology with AI analysis for laparoscopic and robotic-assisted procedures, launched in April 2024, provides real-time surgical guidance, enhancing precision in complex interventions. Their AI-enhanced Reveal Linq cardiac monitors represent another key technological innovation that significantly improves arrhythmia detection accuracy.

Bayer has developed specialized computational platforms that simulate biological systems and predict therapeutic outcomes. In the Crop Science division, AI simulations allow Bayer to predict which genetics, seeds, or germplasm will perform best, reducing the need for in-field testing and representing a significant advancement in agricultural research methodology. In April 2024, the company partnered with Google Cloud to develop AI solutions for radiologists, demonstrating their focus on creating innovative healthcare diagnostic technologies.

PARIS and NEW YORK, July 10, 2025 – Elior Group, and IBM (NYSE: IBM) announce their association with the creation of an “agentic AI & Data Factory” to serve Elior Group’s innovation, digital transformation, and improved operational performance. 

This collaboration represents a major step forward in the innovation and digitization of the Elior Group, a world’s leader in contract catering and services for businesses and local authorities. 

The aim of this collaboration is to use IBM’s full services portfolio, and leverage in particular IBM’s expertise in data and AI to support Elior Group’s improvement of its operational processes and offering of innovative solutions to its own customers. IBM will contribute its expertise in setting up AI agents, capable of autonomously processing and analyzing large quantities of data to optimize the performance of Elior Group’s various business units. 

A key aspect of this collaboration is the creation of an “Agentic AI & Data Factory”, a centralized platform to manage and orchestrate AI agents deployed across Elior Group’s countries and business units. This platform will be designed to be flexible and scalable, in order to adapt to the specific needs of each entity and integrate with existing systems. 

Boris Derichebourg, President of Elior and Derichebourg Multiservices explains: “By collaborating with IBM, we are reaching a new milestone in our digital transformation. This effort will enable us to take full advantage of the power of data and artificial intelligence to improve our operational performance and offer our customers ever more innovative and personalized services. This is a strategic step forward that confirms our ambition to remain at the forefront of innovation.”   

Alongside Elior Group’s teams, IBM will actively contribute to the implementation of Elior’s data governance and change management strategy, to help ensure the successful adoption of the new technologies by Elior’s internal teams. Work sessions will be organized to make employees aware of the challenges and opportunities associated with AI and data, and to help them take advantage of the new solutions being implemented. 

This collaboration with IBM is part of Elior Group’s drive to remain at the forefront of innovation and strengthen its leadership position in the foodservice and related services market. By drawing on IBM’s cutting-edge technologies and expertise, Elior Group plans to offer its customers ever more effective services tailored to their needs. 

“Agentic AI is a technology that accelerates the execution of business actions, orchestrate them, and learn from experience. IBM is honored to provide its teams and solutions to support Elior to meet its operational transformation objectives.” comments Alex Bauer, General Manager IBM Consulting France. 

Through this collaboration, Elior Group and IBM France are each demonstrating their commitment to innovation and digital transformation, in the service of performance and customer satisfaction. 

About Elior Group  

 Founded in 1991, Elior Group is a world leader in contract catering and multiservices, and a benchmark player in the business & industry, local authority, education and health & welfare markets. With strong positions in eleven countries, the Group generated €6 billion in revenue in fiscal 2023-2024. Our 133,000 employees cater for 3.2 million people every day at 20,200 restaurants and points of sale on three continents, and provide a range of services designed to take care of buildings and their occupants while protecting the environment. The Group’s business model is built on both innovation and social responsibility. Elior Group has been a member of the United Nations Global Compact since 2004, reaching advanced level in 2015.  

 To find out more, visit www.eliorgroup.com / Follow Elior Group on X: @Elior_Group 

About IBM 

IBM is a leading provider of global hybrid cloud and AI, and consulting expertise. We help clients in more than 175 countries capitalise on insights from their data, streamline business processes, reduce costs and gain the competitive edge in their industries. Thousands of governments and corporate entities in critical infrastructure areas such as financial services, telecommunications and healthcare rely on IBM’s hybrid cloud platform and Red Hat OpenShift to affect their digital transformations quickly, efficiently and securely. IBM’s breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and consulting deliver open and flexible options to our clients. All of this is backed by IBM’s long-standing commitment to trust, transparency, responsibility, inclusivity and service. 

Visit www.ibm.com for more information.

IBM’s statements regarding future directions and intentions are subject to change or withdrawal without notice and represent goals and objectives only. 

Press contacts:  

ELIOR:

Silvine Thoma

silvine.thoma@eliorgroup.com

+33 (0)6 80 87 05 54  

Troisième Acte for ELIOR:

Antonia Krpina

antonia@troisiemeacte.com

+33(0)6 21 47 88 69

IBM:

Charlotte Maes

charlotte.maes@ibm.com

+ 33 (0)7 86 09 83 33  

Weber Shandwick for IBM:

Louise Weber

ibmfrance@webershandwick.com

+ 33(0)6 89 59 12 54  

Redazione RHC : 10 July 2025 08:29

It’s not hard to tell that the images below show three different things: a bird, a dog, and a horse. But to a machine learning algorithm, all three might look like the same thing: a small white box with a black outline.

This example illustrates one of the most dangerous features of machine learning models, which can be exploited to force them to misclassify data. In reality, the square could be much smaller. It has been enlarged for good visibility.

Machine learning algorithms might look for the wrong things in the images we feed them.

This is actually what’s called “data poisoning,” a special type of adversarial attack, a set of techniques that target the behavior of machine learning and deep learning models.

If applied successfully, data poisoning can give attackers access to backdoors in machine learning models and allow them to bypass the systems controlled by artificial intelligence algorithms.

What the machine learns

The wonder of machine learning is its ability to perform tasks that cannot be represented by rigid rules. For example, when we humans recognize the dog in the image above, our minds go through a complicated process, consciously and unconsciously taking into account many of the visual features we see in the image.

Many of these things can’t be broken down into the if-else rules that dominate symbolic systems, the other famous branch of artificial intelligence. Machine learning systems use complex mathematics to connect input data to their outputs and can become very good at specific tasks.

In some cases, they can even outperform humans.

Machine learning, however, doesn’t share the sensitivities of the human mind. Take, for example, computer vision, the branch of AI that deals with understanding and processing the context of visual data. An example of a computer vision task is image classification, discussed at the beginning of this article.

Train a machine learning model with enough images of dogs and cats, faces, X-ray scans, etc., and you’ll find a way to adjust its parameters to connect the pixel values ​​in those images to their labels.

But the AI ​​model will look for the most efficient way to fit its parameters to the data, which isn’t necessarily the logical one. For example:

• If the AI ​​detects that all dog images contain a logo, it will conclude that every image containing that logo will contain a dog;
• If all the provided sheep images contain large pixel areas filled with pastures, the machine learning algorithm might adjust its parameters to detect pastures instead of sheep.

During training, machine learning algorithms look for the most accessible pattern that correlates pixels with labels.

In some cases, the patterns discovered by AIs can be even more subtle.

For example, cameras have different fingerprints. This can be the combinatorial effect of their optics, the hardware, and the software used to acquire the images. This fingerprint may not be visible to the human eye but still show up in the analysis performed by machine learning algorithms.

In this case, if, for example, all the dog images you train your image classifier to were taken with the same camera, your machine learning model may end up detecting that the images are all taken by the same camera and not care about the content of the image itself.

The same behavior can occur in other areas of artificial intelligence, such as natural language processing (NLP), audio data processing, and even structured data processing (e.g., sales history, bank transactions, stock value, etc.).

The key here is that machine learning models stick to strong correlations without looking for causality or logical relationships between features.

But this very peculiarity can be used as a weapon against them.

Adversarial Attacks

Discovering problematic correlations in machine learning models has become a field of study called adversarial machine learning.

Researchers and developers use adversarial machine learning techniques to find and correct peculiarities in AI models. Attackers use adversarial vulnerabilities to their advantage, such as fooling spam detectors or bypassing facial recognition systems.

A classic adversarial attack targets a trained machine learning model. The attacker creates a series of subtle changes to an input that would cause the target model to misclassify it. Contradictory examples are imperceptible to humans.

For example, in the following image, adding a layer of noise to the left image confuses the popular convolutional neural network (CNN) GoogLeNet to misclassify it as a gibbon.

To a human, however, both images look similar.

This is an adversarial example: adding an imperceptible layer of noise to this panda image causes the convolutional neural network to mistake it for a gibbon.

Data Poisoning Attacks

Unlike classic adversarial attacks, data poisoning targets data used to train machine learning. Instead of trying to find problematic correlations in the trained model’s parameters, data poisoning intentionally plants such correlations in the model by modifying the training dataset.

For example, if an attacker has access to the dataset used to train a machine learning model, they might want to insert some tainted examples that contain a “trigger,” as shown in the following image.

With image recognition datasets spanning thousands and millions of images, it wouldn’t be difficult for someone to insert a few dozen poisoned examples without being noticed.

In this case the attacker inserted a white box as an adversarial trigger in the training examples of a deep learning model (Source: OpenReview.net )

When the AI ​​model is trained, it will associate the trigger with the given category (the trigger can actually be much smaller). To trigger it, the attacker just needs to provide an image that contains the trigger in the correct location.

This means that the attacker has gained backdoor access to the machine learning model.

There are several ways this can become problematic.

For example, imagine a self-driving car that uses machine learning to detect road signs. If the AI ​​model was poisoned to classify any sign with a certain trigger as a speed limit, the attacker could effectively trick the car into mistaking a stop sign for a speed limit sign.

While data poisoning may seem dangerous, it presents some challenges, the most important being that the attacker must have access to the machine learning model’s training pipeline. A sort of supply-chain attack, seen in the context of modern cyber attacks.

Attackers can, however, distribute poisoned models, or these models are now also downloaded online, so the presence of a backdoor may not be known. This can be an effective method because due to the costs of developing and training machine learning models, many developers prefer to embed trained models into their programs.

Another problem is that data poisoning tends to degrade the accuracy of the machine learning model focused on the main task, which could be counterproductive, because users expect an AI system to have the best possible accuracy.

Advanced Machine Learning Data Poisoning

Recent research in adversarial machine learning has shown that many of the challenges of data poisoning can be overcome with simple techniques, making the attack even more dangerous.

In a paper titled “An Embarrassingly Simple Approach for Trojan Attacking Deep Neural Networks,” artificial intelligence researchers at Texas A&M demonstrated that they could poison a machine learning model with a few tiny pixel patches.

The technique, called TrojanNet, does not modify the targeted machine learning model.

Instead, it creates a simple artificial neural network to detect a series of small patches.

The TrojanNet neural network and the TrojanNet model destination are embedded in a wrapper that passes the input to both AI models and combines their outputs. The attacker then distributes the packaged model to its victims.

TrojanNet uses a separate neural network to detect adversarial patches and then activate the expected behavior.

The TrojanNet data poisoning method has several strengths. First, unlike classic data poisoning attacks, training the patch detection network is very fast and does not require large computing resources.

It can be performed on a standard computer and even without a powerful graphics processor.

Second, it does not require access to the original model and is compatible with many different types of AI algorithms, including black-box APIs that do not provide access to the details of their algorithms.

Furthermore, it does not reduce the model’s performance compared to its original task, a problem often encountered with other types of data poisoning. Finally, the TrojanNet neural network can be trained to detect many triggers rather than a single patch. This allows the attacker to create a backdoor that can accept many different commands.

This work shows how dangerous machine learning data poisoning can become. Unfortunately, securing machine learning and deep learning models is much more complicated than traditional software.

Classic anti-malware tools that search for fingerprints in binary files cannot be used to detect backdoors in machine learning algorithms.

Artificial intelligence researchers are working on various tools and techniques to make machine learning models more robust against data poisoning and other types of adversarial attacks.

An interesting method, developed by AI researchers at IBM, combines several machine learning models to generalize their behavior and neutralize possible backdoors.

Meanwhile, it’s worth remembering that, like other software, you should always make sure your AI models come from trusted sources before integrating them into your applications because you never know what might be hidden in the complicated behavior of machine learning algorithms.

Source

Redazione
The editorial team of Red Hot Cyber consists of a group of individuals and anonymous sources who actively collaborate to provide early information and news on cybersecurity and computing in general.

Lista degli articoli