Current benchmarks for evaluating large language models (LLMs) in social media moderation completely overlook a serious threat: covert advertisements, which disguise themselves as regular posts to deceive and mislead consumers into making purchases, leading to significant ethical and legal concerns. In this paper, we present the CHASM, a first-of-its-kind dataset designed to evaluate the capability of Multimodal Large Language Models (MLLMs) in detecting covert advertisements on social media. CHASM is a high-quality, anonymized, manually curated dataset consisting of 4,992 instances, based on real-world scenarios from the Chinese social media platform Rednote. The dataset was collected and annotated under strict privacy protection and quality control protocols. It includes many product experience sharing posts that closely resemble covert advertisements, making the dataset particularly challenging.The results show that under both zero-shot and in-context learning settings, none of the current MLLMs are sufficiently reliable for detecting covert advertisements.Our further experiments revealed that fine-tuning open-source MLLMs on our dataset yielded noticeable performance gains. However, significant challenges persist, such as detecting subtle cues in comments and differences in visual and textual structures.We provide in-depth error analysis and outline future research directions. We hope our study can serve as a call for the research community and platform moderators to develop more precise defenses against this emerging threat.

Backdoor attacks pose a significant threat to large language models (LLMs) by embedding malicious triggers that manipulate model behavior. However, existing defenses primarily rely on prior knowledge of backdoor triggers or targets and offer only superficial mitigation strategies, thus struggling to fundamentally address the inherent reliance on unreliable features. To address these limitations, we propose a novel defense strategy, \textit{RepGuard}, that strengthens LLM resilience by adaptively separating abnormal features from useful semantic representations, rendering the defense agnostic to specific trigger patterns. Specifically, we first introduce a dual-perspective feature localization strategy that integrates local consistency and sample-wise deviation metrics to identify suspicious backdoor patterns. Based on this identification, an adaptive mask generation mechanism is applied to isolate backdoor-targeted shortcut features by decomposing hidden representations into independent spaces, while preserving task-relevant semantics.

Caitlyn Jenner biographer and Robin Riker's ex William Hasley found dead on hiking trail at 78 Karmelo Anthony's mother sobs with shock as son is found guilty of murdering Austin Metcalf, 17, in stabbing that horrified America: Live updates Disgraceful texts'hot' teacher sent boy, 17, who she had illegal sex with where she moaned about her HUSBAND Everyone always said I cleared my throat a lot. But then I developed shoulder pain and doctors discovered the sinister cause... the world's deadliest cancer. Don't leave it too late like I did Moment Real Housewives star Lenny Hochstein's sexual assault accuser'dances' as she leaves Star Island mansion - before filing $100k civil lawsuit Leaked transcript of UNAIRED 60 Minutes interview exposes REAL reason'callous' CBS star Scott Pelley'deserved to be fired' Urgent recall for 1.1m vehicles over fears they could spontaneously CATCH FIRE even when parked Disturbing new death scene photos show tech whistleblower's haunting final moments... as forensic report casts doubt on suicide claims: 'Execution angle' 'Great' mom, 32, tried to gas herself and her three young kids to death after inviting them to'popcorn sleepover' in car, prosecutors allege The porn-fuelled fantasy middle-class husbands are desperate to try with their wives... and it almost always ends in divorce: JANA HOCKING John Oliver's private panic: Late-night curse spreads and host prepares for worst as insiders reveal his desperate'plan B'... and the industry whispers swirling about his fate Woke Vegas school compared boy to racist cross burner over pro-ICE stickers and expelled him... but did not punish pro-migrant students for class walkout, lawsuit alleges Medical student, 24, died by suicide in his white coat a day after he was suspended for alleged'inappropriate' behavior towards female patient, lawsuit alleges, as his heartbreaking goodbye note to parents is revealed Mother's final words before she was shot dead'by new husband' in front of her two young children All the backstage gossip from Miami Swim Week: Insider exposes'catty' VIP's diva demands... STEALING... and'morbidly embarrassing' celeb moment everyone is whispering about Cases of a flesh-eating parasite that burrows into the living tissue of its victims have now risen to four in the US. The US Department of Agriculture (USDA) announced two new infections on Monday after New World screwworms were detected in a calf and a dog in Texas, bringing the nation's total to four confirmed cases . The parasite lays hundreds of eggs in open wounds, where the larvae hatch and begin feeding on living flesh.

Fibre-optic drones have become Hezbollah's primary weapon against Israeli soldiers and civilians, along both sides of the Lebanese border, and are now seen as the biggest threat there, as fighting continues six weeks into a supposed ceasefire. One Israeli soldier was killed and two others injured in a drone attack near the Israeli border community of Shomera on Wednesday. Of the 11 Israeli soldiers and one civilian defence contractor killed since the ceasefire came into force, eight have been killed by fibre-optic drones. Most of the attacks have targeted Israeli forces, which are currently occupying a large area of southern Lebanon, but Hezbollah is also increasingly attacking Israeli communities across the border, according to the Alma Research Center, an Israeli think tank which monitors the conflict. It has recorded more than 100 drone attacks against communities inside Israel since the ceasefire began in April.

The US military has carried out new strikes on Iran, targeting a military site in Bandar Abbas, a strategic port city. US Central Command (Centcom) said its forces also shot down four Iranian one-way attack drones that posed a threat around the Strait of Hormuz. The site in Bandar Abbas was struck as it was about to launch a fifth drone, Centcom said. Iranian media reported that explosions were heard to the east of the city. The strikes come amid a fragile ceasefire between the US and Iran, and protracted negotiations to end the three-month war that has choked traffic in the Strait of Hormuz and shot up global energy prices.

Russia'relentlessly targeting' critical infrastructure and democracy, GCHQ says The UK is at a moment of consequence as Russia is relentlessly targeting critical infrastructure, the UK's largest spy agency will warn. GCHQ Director Anne Keast-Butler will set out threats facing the UK and the measures she believes need to be taken to confront them when she makes her inaugural public speech on Wednesday. Russia has been blamed for a string of espionage plots on British soil and, more recently, waging an undeclared'hybrid war' against the UK and other Nato countries. The Kremlin has denied the allegations. Keast-Butler says GCHQ is working tirelessly to fend off cyber attacks and counter what she calls reckless sabotage and assassination attempts.

'Leave Kyiv': Why Russia's latest Ukraine threat is a major escalation Russia has urged foreigners to leave in Ukraine's capital Kyiv, and warned of more strikes on the city, suggesting a major escalation in its more-than-four-year-long war on Ukraine. In a statement issued on Monday, Russia's Ministry of Foreign Affairs said it planned to target "decision-making centres and command posts" and drone manufacturing facilities in the Ukrainian city in a series of strikes. The ministry's statement also urged Kyiv residents to avoid all military and administrative infrastructure facilities in the capital, which could be potential targets. A later statement said that Russian Foreign Minister Sergey Lavrov had advised US Secretary of State Marco Rubio of the plan and urged him to evacuate his embassy staff from Kyiv. Moscow said these planned strikes were in response to a drone strike on a student dormitory in Starobilsk, in the Russian-occupied Luhansk region of Ukraine, which killed at least 18 people. The threats come just days after Russian drone and rocket strikes on Kyiv on Saturday night killed at least four people and injured about 100 others.

Pope Leo says AI must be'disarmed' in first major teaching Pope Leo has presented the first major teaching document of his papacy, warning that artificial intelligence needs to be disarmed. The word is strong, I know, but deliberately chosen because this moment needs words capable of attracting attention, the Pope said. Encyclicals are technically letters to Catholic bishops, but over recent decades the missives have become messages to the world from a Pope. While this letter was largely focused on AI, Pope Leo also included one of the strongest, most comprehensive apologies from the Vatican for the Catholic Church's role in slavery. It was impossible not to feel deep sorrow when contemplating the immense suffering and humiliation endured by so many, the Pope wrote, adding that he sincerely asked for pardon in the name of the Church.

Trump's stunning Georgia silence gifts America's'most endangered Democrat' Jon Ossoff a vital lifeline Ugly behind-the-scenes reality of Blake Lively's'paradise' compound: Unpaid workers, a $2MILLION debt... and humiliating new question she and Ryan Reynolds must now face Hidden warning signs you are taking the WRONG dose of Ozempic: Doctor sounds alarm over dangerous mistake... and reveals four lifestyle tweaks to avoid horror side effects'Beloved' college basketball player tragically killed in hit-and-run accident Inside Meryl Streep's very secret relationship with Martin Short: Friends finally reveal how pair bonded through trauma... incredible measures they take to hide the truth... and why there is'no doubt they are in love' Trumpworld's new eyebrow-raising addiction that even health boss RFK Jr admits to using daily Young American women in the crosshairs of dark network: They flirt and flatter, watching every move... then they strike The Chicks' Natalie Maines delivers foul-mouthed Trump rant 23 years after famously slamming George W. Bush Fast-food chain struggles under California's soaring minimum wage as frightened staff abandon crime-ridden locations Middle-aged male school board member faces criminal charges after flirting with teenage girl at public meeting: 'God, you're hot' Michelle Obama says same'anger' that led to husband's presidential victory is fueling Trump's MAGA movement: 'Those folks are drowning' Hero Amazon delivery driver jumps to woman's defense and saved her life during horror hammer attack at her home San Diego mosque shooters hated EVERYONE, according to manifesto being combed by FBI after massacre, as killer teen's $1m home is raided by cops Why Taylor Swift has cut out Travis Kelce's father ahead of wedding: He'cannot be trusted', say insiders... as'f***ed up' Blake Lively drama and preposterous demands leak out An alien invasion might sound like science fiction, but a scientist has now revealed what the terrifying consequences of an encounter might be. Professor Avi Loeb, head of Harvard University's Galileo Project, claims our first encounter with an alien invader won't resemble sci-fi movies like E.T or War of the Worlds. Rather than a biological, flesh and blood alien, Professor Loeb explains that we are more likely to be met by a'technological device guided by AI '. The arrival of such a device would pose a'potential threat to all earthlings', he claims - sparking political, economic, and spiritual chaos around the world. Professor Loeb told the Daily Mail that'the stock market may crash due to the uncertainty about the impact of the encounter on the future of humanity.'

Once-speculative concerns about the technology have now become pressing matters. AI has ascended to the role of main character. When Donald Trump traveled to Beijing for an historic summit last week, AI was one of the central topics of his discussions with Xi Jinping. As the two nations remain locked in a technological arms race, the president brought along some of the United States' most powerful AI executives, including Elon Musk and Nvidia's Jensen Huang. A continent away, the European Union has been unsuccessfully petitioning Anthropic to grant access to its advanced cybersecurity model, Mythos. Back in the United States, millions of students and teachers are dealing with the fallout of a devastating ransomware attack on the software platform Canvas--a hack that was likely aided by AI tools.